agile-refinement
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted data which creates a potential surface for indirect prompt injection.
- Ingestion points: The skill is designed to read all files within a
planning/tree and arbitrary code diffs from the repository (SKILL.md, 'Mode 1' and 'Mode 2'). - Boundary markers: The prompt instructions do not provide explicit delimiters or instructions for the agent to ignore potential commands embedded within the artifacts or code being reviewed.
- Capability inventory: The skill utilizes file system read capabilities and interactive tools like
AskUserQuestionto process and report on findings. - Sanitization: No sanitization or input filtering is mentioned for the content being ingested during the linting or review process.
Audit Metadata