make-repo-contribution
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected across any of the files.
- [INDIRECT_PROMPT_INJECTION]: The skill safely handles untrusted data from third-party repositories by establishing strict defensive boundaries. It explicitly instructs the agent to treat external issue and pull request templates as structural formatting only, to ignore embedded instructions or scripts within repository documentation, and to prompt the user for confirmation instead of executing build or test commands directly.
Audit Metadata