tracer-to-spec
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external sources, such as URLs, issue trackers, and local files (e.g., Wayfinder maps, ticket bodies, and resolution comments), to synthesize project specifications.
- Ingestion points: As described in
SKILL.md(Step 1), the skill hydrates data from a provided URL, issue number, or local path, and fetches full bodies and comments for resolved tickets. - Boundary markers: The instructions do not include explicit delimiters or warnings to ignore embedded instructions within the fetched external content, creating a surface where malicious text in a ticket or map could influence the agent's behavior.
- Capability inventory: The skill is capable of writing files to the local repository (specifically within
.tracer/anddocs/directories) and publishing synthesized content to an external issue tracker. - Sanitization: There is no mention of sanitizing or validating the ingested content before it is processed and written into the final specification document.
Audit Metadata