review-roadmap
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze a user-provided file (roadmap path), which serves as an entry point for untrusted data into the agent's context.
- Ingestion points: The
[roadmap file path]argument specified in the frontmatter and used throughout the instructions. - Boundary markers: The instructions lack explicit delimiters or warnings to the subagents to ignore or treat instructions within the roadmap file as data rather than commands.
- Capability inventory: The skill dispatches three subagents and utilizes a
/researchtool to perform external lookups based on the file content. - Sanitization: There is no evidence of sanitization, validation, or filtering of the content read from the roadmap file before it is passed to the subagents.
Audit Metadata