finding-skill-opportunities

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill runs its own bundled bash scripts (git-signals.sh and scan-workflows.sh) to perform repository audits. These scripts are read-only and utilize standard git and shell utilities.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to the ingestion of untrusted repository data.
  • Ingestion points: Data is ingested from git logs (commit subjects) and various repository files (Makefile targets, script keys in package.json, and documentation headers).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are included in the results presented to the agent.
  • Capability inventory: The skill's scripts are read-only; however, the agent's interpretation of the collected signals could be manipulated by malicious text in the repo history.
  • Sanitization: No sanitization or filtering is applied to the data extracted from the repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 05:43 PM
Security Audit — agent-trust-hub — finding-skill-opportunities