ajiang-git-commit-pr
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources including Git logs, diffs, and issue references. This content could potentially contain malicious instructions intended to mislead the agent.\n
- Ingestion points:
SKILL.md(Step 1, Mode 1) andreferences/pr-sync.md(Step 2) describe readinggit diff,git status,git log, and analyzing logic conflicts in source code.\n - Boundary markers: The skill does not define formal delimiters for external content but includes strict instructions to only process changes relevant to the current task and to avoid overriding user work.\n
- Capability inventory: The skill utilizes
git commit,git push(SKILL.md), andgh pr create(SKILL.md, Mode 2) to modify the repository state and interact with remote GitHub services.\n - Sanitization: Defensive measures are present in
SKILL.md(Mode 2, Step 6) andreferences/pr-sync.md(Step 5), which require the agent to manually verify target URLs, commit SHAs, and re-validate integrations if the upstream changes.
Audit Metadata