pr-summary
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted input from git diffs (
main...HEAD) and internal state files (.agents/state.json), creating a surface for indirect prompt injection where adversarial code comments could influence the summary output. - Ingestion points: Git diff output and
.agents/state.jsonfile content. - Boundary markers: Absent; the instructions do not define delimiters or provide specific instructions to treat the git output as data rather than instructions.
- Capability inventory: Primarily restricted to text generation for pull request descriptions; no execution or network capabilities are present in the provided file.
- Sanitization: No sanitization or filtering is applied to the git diff content before it is processed by the agent.
Audit Metadata