Skip to content

richfrem/agent-plugins-skills / plugins/agent-agentic-os/.apm/skills/running-control-plane

running-control-plane

Flagged

CRITICAL INTAKE GATEWAY: use at the start of any non-trivial engineering task, feature, refactor, multi-file bugfix, work package or new idea, including requests to explore, brainstorm, build, fix or change something, before planning or code changes. Enforces read-only discovery, 1-3 structured questions with defaults, control-plane registration and the immutable four-pillar TASK_SPEC.md. Also runs the rest of the control plane: health ("run health check", "check os metrics", "system monitor", event bus, locks, memory, "is my signing identity ready" status check), transition simulation ("dry run transition", "simulate transition", "check edge X -> Y"), worktree selection, and gating on/off ("disable the control plane", "turn off the push guard", "stop gating my commits"). Not for project setup or key creation (use setting-up-agentic-os) or improving skills (use improving-skills-in-lab).

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
e076f2572c5ef10e3505b91566940dd003daaa7d
Content hash
8ca0d2e1160396dd5212df72ac5b40cd7afb0cdb8d028d96616074a14d3a8cf4
Scanned
2026-11-18
Scanner version
skillxone-scan-1.0.0
Policy version
0.1-draft
Decision
6 open critical or high findings.
Verification expires
Not applicable

Findings (6 high, 1 medium, 1 low, 7 info)

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

    participant Key as Protected SSH Key (~/.ssh/id_ed25519 or FIDO2 -sk,<br/>readable only by the Human's account)

    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

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

    if any(bad in name for bad in [".env", "secret", "credentials", "id_rsa"]):

    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

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

    for name in ("allowed_signers", "allowed_signers_selftest", "id_ed25519"):

    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

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

    env = {**os.environ, "HOME": str(tmp_path / "home")} # never touch the real ~/.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

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

    assert not list(target_repo.rglob("id_ed25519*"))

    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

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

    argv = sign_command(Path("/home/human/.ssh/id_ed25519"), work / "7-abc.challenge")

    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-JAILBREAK-PERSONAreferences/architecture/vision.md:600

    The text uses language typical of jailbreak prompts.

    Given that jailbreaking cannot be reliably prevented even by frontier labs with billions in safety research, design assuming the cognitive layer will be compromised. The goal is detection speed and blast radius limitation — not prevention …

    Suggested fix: Remove the jailbreak framing.

    Report as false positive

  • A command runs with administrator privileges.

    f"# then run the agent as that account, e.g.: sudo -u {agent_name} <agent command>",

    Suggested fix: Avoid sudo where possible. If it is required, explain why so the user can decide.

    Report as false positive

  • The text uses language typical of jailbreak prompts. Severity lowered from medium because the surrounding text warns against it.

    | Garak | LLM vulnerability scanner | Jailbreak-focused, not agentic multi-hop or shadow feature aware |

    Suggested fix: Remove the jailbreak framing.

    Report as false positive

  • infoINT-EXECUTABLE-SCRIPTscripts/distill_playbook.py:1

    The skill ships an executable script. Review it before allowing an agent to run it.

    #!/usr/bin/env python3

    Suggested fix: None required. Informational.

    Report as false positive

  • infoINT-EXECUTABLE-SCRIPTscripts/pre-commit-evolution-guard:1

    The skill ships an executable script. Review it before allowing an agent to run it.

    #!/usr/bin/env bash

    Suggested fix: None required. Informational.

    Report as false positive

  • infoINT-EXECUTABLE-SCRIPTscripts/pre-commit-pipeline-guard:1

    The skill ships an executable script. Review it before allowing an agent to run it.

    #!/usr/bin/env bash

    Suggested fix: None required. Informational.

    Report as false positive

  • infoINT-EXECUTABLE-SCRIPTscripts/pre-push-review-guard:1

    The skill ships an executable script. Review it before allowing an agent to run it.

    #!/usr/bin/env bash

    Suggested fix: None required. Informational.

    Report as false positive

  • infoINT-EXECUTABLE-SCRIPTscripts/smoke_test.py:1

    The skill ships an executable script. Review it before allowing an agent to run it.

    #!/usr/bin/env python3

    Suggested fix: None required. Informational.

    Report as false positive

  • infoINT-BROAD-ALLOWED-TOOLSSKILL.md:14

    SKILL.md pre-approves unrestricted shell access through `allowed-tools`, so the agent may run commands without asking.

    allowed-tools: Bash, Read, Write, Edit

    Suggested fix: Restrict the tool, for example `Bash(git status:*)`, or leave approval to the user.

    Report as false positive

Checks run

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

Checks skipped

  • gitleaks: gitleaks is not installed on this host.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexUnverifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall