pr-description-concise-markdown
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill consumes external data from git history and code changes, which acts as a potential vector for indirect prompt injection.
- Ingestion points: Git commit messages and code diffs accessed through the Bash tool (SKILL.md).
- Boundary markers: None are provided in the instructions to help the agent differentiate between the data being summarized and the agent's own instructions.
- Capability inventory: The skill is restricted to read-only git operations via the
allowed-toolsconfiguration. It lacks the ability to write files or perform network operations. - Sanitization: The skill does not implement sanitization or filtering for the git data it processes.
Audit Metadata