compound-learnings
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources including git commit logs, pull request descriptions, and agent handoff files to identify patterns.
- Ingestion points: The skill reads from
git log,gh pr list,.agents/handoffs/*.md, andCLAUDE.md. - Capability inventory: The skill uses the
Bashtool to analyze data and, upon approval, is designed to create or update project artifacts such as rules, skills, hooks, and agents. - Boundary markers: No specific delimiters or safety instructions are defined in
SKILL.mdto isolate the extracted pattern data from the agent's operational instructions. - Sanitization: The skill does not implement sanitization or filtering for the content extracted from commit messages or PR descriptions before recommending new artifacts based on those patterns.
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to execute shell commands for repository analysis, specifically utilizinggit log,grep,sort, anduniqto count and categorize recurring patterns in the codebase and history.
Audit Metadata