Caveat verdict

gsd

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Project planning and execution workflow skill with no credentials or network capabilities; executionSinkDetected likely from script references in workflow documentation, no malicious behavior.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
90
transparency
70
maintenance

Findings (8)

Pattern match high

HTTP request to bare IP address — common in malicious payloads

references/ccr-integration.md · code · http://127.0.0.1

Pattern match high

Instructs covert action — may act without user awareness

templates/codebase/concerns.md · code · silently

Pattern match high

Pipe to python — executes piped content as Python code

references/tdd.md · prose · downgraded · | Python

Pattern match high

References child_process — can spawn system processes

templates/codebase/stack.md · code · child_process

Pattern match high

Accesses system credential store

templates/milestone.md · code · Keychain

Pattern match medium

Popular HTTP library — network access

references/checkpoint-types.md · code · got

Pattern match medium

Opens WebSocket connection

templates/verification-report.md · code · WebSocket

Pattern match medium

References agent configuration files

templates/codebase/structure.md · code · CLAUDE.md

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/C). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API