request-refactor-plan
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from both the user interview process and the local repository files.
- Ingestion points: User-provided problem descriptions (Step 1) and codebase exploration (Steps 2 and 6) in
SKILL.md. - Boundary markers: None detected. The skill does not use delimiters or instructions to ignore embedded commands in the data it processes.
- Capability inventory: The skill has read access to the local filesystem and the ability to create external content via GitHub issues.
- Sanitization: No explicit sanitization or validation of the ingested content is mentioned before it is used to generate the GitHub issue.
- [EXTERNAL_DOWNLOADS]: The skill performs network operations to interact with GitHub for issue creation.
- Evidence: Step 8 in
SKILL.mdexplicitly instructs the agent to create a GitHub issue with the generated refactor plan.
Audit Metadata