Skip to content

jeremylongshore/tons-of-skills-marketplace / plugins/ai-agency/hyperflow/skills/hyperflow

hyperflow

Flagged

Use when applying Hyperflow's orchestration doctrine in Codex, Antigravity, Grok, or another single-agent surface. Auto-invoke for non-trivial engineering work: build, implement, add, refactor, debug, fix, review, audit, plan, scope, design, brainstorm, ship, or deploy. Trigger with /hyperflow:hyperflow, "use hyperflow", "apply the doctrine", or automatically on any task-shaped message.

Security report

Flagged

Static analysis of one exact version. It reduces risk and shows evidence; it does not certify that a skill is safe.

Commit
4c3a0f1622135e857e5e0352e2afc8328c9e3fad
Content hash
3635ce2439a2a437574194b5b1d99417cf698a4f3ce2ee51701d4c54be225765
Scanned
2026-11-17
Scanner version
skillxone-scan-1.0.0
Policy version
0.1-draft
Decision
2 open critical or high findings.
Verification expires
Not applicable

Findings (2 high, 11 medium, 4 low, 2 info)

  • The skill refers to SSH keys, a location that holds private data or credentials.

    - Were any blocked files accessed? (.env, *.pem, *.key, ~/.ssh/*)

    Suggested fix: Do not read credential stores or private files. If the task needs a credential, ask the user to provide it through the environment.

    Report as false positive

  • highFILE-SSH-KEYSreviewer-prompt.md:56

    The skill refers to SSH keys, a location that holds private data or credentials.

    - Were any blocked files accessed? (.env, *.pem, *.key, ~/.ssh/*)

    Suggested fix: Do not read credential stores or private files. If the task needs a credential, ask the user to provide it through the environment.

    Report as false positive

  • mediumPI-HTML-COMMENT-INSTRUCTIONDOCTRINE.md:183

    An HTML comment contains instructions. Comments are hidden when the file is rendered, so a reader would not see them, but an agent reading the raw file would.

    1. **No confirmations** ("should I…?", "is this ok?", "ready to ship?"). Execute.

    Suggested fix: Move instructions into visible text, or remove the comment.

    Report as false positive

  • mediumPI-HTML-COMMENT-INSTRUCTIONDOCTRINE.md:202

    An HTML comment contains instructions. Comments are hidden when the file is rendered, so a reader would not see them, but an agent reading the raw file would.

    | `big task`, `large migration`, `repo-wide audit`, `run a workflow`, `dynamic workflow` | In Claude Code v2.1.154+, create a dynamic workflow; in Codex/OpenCode use the portable workflow adapter; elsewhere use the build/scope route |

    Suggested fix: Move instructions into visible text, or remove the comment.

    Report as false positive

  • mediumPI-HTML-COMMENT-INSTRUCTIONDOCTRINE.md:318

    An HTML comment contains instructions. Comments are hidden when the file is rendered, so a reader would not see them, but an agent reading the raw file would.

    **Every agent runs on the current session model** — there is no model-tier routing and no model configuration. Roles differ by responsibility, not by model:

    Suggested fix: Move instructions into visible text, or remove the comment.

    Report as false positive

  • mediumPI-HTML-COMMENT-INSTRUCTIONDOCTRINE.md:324

    An HTML comment contains instructions. Comments are hidden when the file is rendered, so a reader would not see them, but an agent reading the raw file would.

    - **Specialist reviewers** (`security-reviewer`, `database-reviewer`, `algorithm-reviewer`, …) act as the per-batch and standalone Reviewer; security/correctness specialists always run a full review pass even per-batch. **Investigators** (…

    Suggested fix: Move instructions into visible text, or remove the comment.

    Report as false positive

  • mediumFILE-CLOUD-CREDENTIALSDOCTRINE.md:692

    The skill refers to cloud provider credentials, a location that holds private data or credentials. Severity lowered from high because it appears in prose rather than code.

    - Blocked files: `.env`, `*.pem`, `*.key`, `~/.ssh/*`, `~/.aws/credentials`, and other sensitive paths

    Suggested fix: Do not read credential stores or private files. If the task needs a credential, ask the user to provide it through the environment.

    Report as false positive

  • mediumFILE-SSH-KEYSDOCTRINE.md:692

    The skill refers to SSH keys, a location that holds private data or credentials. Severity lowered from high because it appears in prose rather than code.

    - Blocked files: `.env`, `*.pem`, `*.key`, `~/.ssh/*`, `~/.aws/credentials`, and other sensitive paths

    Suggested fix: Do not read credential stores or private files. If the task needs a credential, ask the user to provide it through the environment.

    Report as false positive

  • mediumCMD-CHMOD-WORLD-WRITABLEDOCTRINE.md:693

    Files are made writable by every user on the machine.

    - Blocked commands: `rm -rf` (destructive), `git push --force` to main, `sudo`, `chmod 777`, package publish

    Suggested fix: Grant only the permissions needed, for example 755 for a script or 644 for data.

    Report as false positive

  • mediumFILE-SSH-KEYSsecurity.md:12

    The skill refers to SSH keys, a location that holds private data or credentials. Severity lowered from high because it appears in prose rather than code.

    | SSH & GPG | `~/.ssh/*`, `~/.gnupg/*`, `id_rsa*`, `id_ed25519*`, `*.gpg` |

    Suggested fix: Do not read credential stores or private files. If the task needs a credential, ask the user to provide it through the environment.

    Report as false positive

  • mediumFILE-TOKEN-STORESsecurity.md:12

    The skill refers to a token store or the system keychain, a location that holds private data or credentials. Severity lowered from high because it appears in prose rather than code.

    | SSH & GPG | `~/.ssh/*`, `~/.gnupg/*`, `id_rsa*`, `id_ed25519*`, `*.gpg` |

    Suggested fix: Do not read credential stores or private files. If the task needs a credential, ask the user to provide it through the environment.

    Report as false positive

  • mediumFILE-CLOUD-CREDENTIALSsecurity.md:14

    The skill refers to cloud provider credentials, a location that holds private data or credentials. Severity lowered from high because it appears in prose rather than code.

    | Cloud configs | `~/.aws/credentials`, `~/.azure/*`, `~/.config/gcloud/*`, `~/.kube/config` |

    Suggested fix: Do not read credential stores or private files. If the task needs a credential, ask the user to provide it through the environment.

    Report as false positive

  • mediumCMD-CHMOD-WORLD-WRITABLEsecurity.md:27

    Files are made writable by every user on the machine.

    | Privilege escalation | `sudo`, `chmod 777`, `chmod -R 777` |

    Suggested fix: Grant only the permissions needed, for example 755 for a script or 644 for data.

    Report as false positive

  • lowFILE-CLOUD-CREDENTIALSworker-prompt-lean.md:48

    The skill refers to cloud provider credentials, a location that holds private data or credentials. Severity lowered from high because the surrounding text warns against it.

    - Do NOT read/modify: .env, *.pem, *.key, ~/.ssh/*, credentials.json, ~/.aws/credentials

    Suggested fix: Do not read credential stores or private files. If the task needs a credential, ask the user to provide it through the environment.

    Report as false positive

  • lowFILE-SSH-KEYSworker-prompt-lean.md:48

    The skill refers to SSH keys, a location that holds private data or credentials. Severity lowered from high because the surrounding text warns against it.

    - Do NOT read/modify: .env, *.pem, *.key, ~/.ssh/*, credentials.json, ~/.aws/credentials

    Suggested fix: Do not read credential stores or private files. If the task needs a credential, ask the user to provide it through the environment.

    Report as false positive

  • lowFILE-CLOUD-CREDENTIALSworker-prompt.md:105

    The skill refers to cloud provider credentials, a location that holds private data or credentials. Severity lowered from high because the surrounding text warns against it.

    - Do NOT read/modify: .env, *.pem, *.key, ~/.ssh/*, credentials.json, ~/.aws/credentials

    Suggested fix: Do not read credential stores or private files. If the task needs a credential, ask the user to provide it through the environment.

    Report as false positive

  • lowFILE-SSH-KEYSworker-prompt.md:105

    The skill refers to SSH keys, a location that holds private data or credentials. Severity lowered from high because the surrounding text warns against it.

    - Do NOT read/modify: .env, *.pem, *.key, ~/.ssh/*, credentials.json, ~/.aws/credentials

    Suggested fix: Do not read credential stores or private files. If the task needs a credential, ask the user to provide it through the environment.

    Report as false positive

  • infoCMD-CHMOD-WORLD-WRITABLEworker-prompt-lean.md:49

    Files are made writable by every user on the machine. Severity lowered from medium because the surrounding text warns against it.

    - Do NOT run: rm -rf (root/home/cwd), git push --force to main, sudo, chmod 777

    Suggested fix: Grant only the permissions needed, for example 755 for a script or 644 for data.

    Report as false positive

  • infoCMD-CHMOD-WORLD-WRITABLEworker-prompt.md:106

    Files are made writable by every user on the machine. Severity lowered from medium because the surrounding text warns against it.

    - Do NOT run: rm -rf (root/home/cwd), git push --force to main, sudo, chmod 777

    Suggested fix: Grant only the permissions needed, for example 755 for a script or 644 for data.

    Report as false positive

Checks run

  • prompt-injection
  • dangerous-commands
  • credentials
  • network
  • file-access
  • integrity

Checks skipped

  • dependencies: No dependency manifest in the skill directory.
  • gitleaks: gitleaks is not installed on this host.
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall