review-pr
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection surface detected where the skill ingests external data from GitHub comments.
- Ingestion points: PR comments and review bodies are fetched via
gh apiinSKILL.md. - Boundary markers: Absent; the skill lacks delimiters to separate external data from instructions.
- Capability inventory: The agent has access to shell execution (gh, git), network operations, and instructions to modify and push code.
- Sanitization: Absent; the agent is instructed to evaluate and fix bugs based on external feedback without prior validation.
Audit Metadata