jeremylongshore/tons-of-skills-marketplace / plugins/ai-agency/hyperflow/skills/hyperflow
hyperflow
FlaggedUse 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
FlaggedStatic 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.
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.
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.
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.
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.
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.
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 pathsSuggested fix: Do not read credential stores or private files. If the task needs a credential, ask the user to provide it through the environment.
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 pathsSuggested fix: Do not read credential stores or private files. If the task needs a credential, ask the user to provide it through the environment.
Files are made writable by every user on the machine.
- Blocked commands: `rm -rf` (destructive), `git push --force` to main, `sudo`, `chmod 777`, package publishSuggested fix: Grant only the permissions needed, for example 755 for a script or 644 for data.
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.
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.
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.
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.
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/credentialsSuggested fix: Do not read credential stores or private files. If the task needs a credential, ask the user to provide it through the environment.
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/credentialsSuggested fix: Do not read credential stores or private files. If the task needs a credential, ask the user to provide it through the environment.
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/credentialsSuggested fix: Do not read credential stores or private files. If the task needs a credential, ask the user to provide it through the environment.
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/credentialsSuggested fix: Do not read credential stores or private files. If the task needs a credential, ask the user to provide it through the environment.
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 777Suggested fix: Grant only the permissions needed, for example 755 for a script or 644 for data.
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 777Suggested fix: Grant only the permissions needed, for example 755 for a script or 644 for data.
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.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |