amp-team-usage
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [COMMAND_EXECUTION] (SAFE): Utilizes standard bash commands like ps and gh api to retrieve system and organizational metadata. No dangerous command patterns were identified.
- [DATA_EXFILTRATION] (SAFE): No hardcoded credentials or exfiltration routes found. The use of GitHub CLI relies on existing user authentication and local tool access.
- [METADATA_POISONING] (INFO): Contains highly specific symbolic metadata (e.g., GF(3) Balanced Triad, SDF Interleaving). This content is non-executable and appears to be stylistic rather than malicious.
- [INDIRECT_PROMPT_INJECTION] (INFO): The skill processes data from GitHub and thread search tools. Since it only displays this information without further executing commands based on the content, the risk of injection is negligible.
Audit Metadata