standup-notes

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes standard git and GitHub CLI commands to retrieve repository metadata and recent activity.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface (Category 8) as it processes data from commit messages and pull request titles.
  • Ingestion points: Git log, git diff, and GitHub PR titles (SKILL.md).
  • Boundary markers: No delimiters or isolation instructions are provided for processed data.
  • Capability inventory: The skill is limited to text generation; it has no file-write, remote code execution, or network exfiltration capabilities (SKILL.md).
  • Sanitization: No sanitization is performed on the ingested text.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 08:07 PM
Security Audit — agent-trust-hub — standup-notes