skill-improvement-plan
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and parse external content from review and audit reports, creating a potential surface for indirect prompt injection.
- Ingestion points: Processes markdown feedback from external reports (e.g., skill-deep-review, skill-audit) and manual user notes as defined in Step 1 of the process in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or isolation techniques for the external content being parsed to prevent embedded instructions from being followed.
- Capability inventory: The skill is authorized to use
Read,Grep,Glob, andWritetools to analyze files and generate the resulting improvement plan. - Sanitization: There is no evidence of sanitization, filtering, or escaping for the data extracted from the reports before it is formatted into the output plan.
Audit Metadata