pr-comment-resolver
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and act upon untrusted data (pull request comments) to modify the codebase.
- Ingestion points: Pull request comments are analyzed and used as instructions for code implementation in SKILL.md.
- Boundary markers: There are no explicit delimiters or instructions to ignore potential commands embedded within the comments being resolved.
- Capability inventory: The agent is tasked with implementing code changes across the project files, which could be abused if a malicious comment overrides its intended behavior.
- Sanitization: The instructions do not specify any validation or sanitization of the requested changes before they are implemented.
Audit Metadata