trellis-update-spec
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest data from existing documentation files, creating a vulnerability surface where malicious instructions embedded in those files could influence agent behavior.
- Ingestion points: The agent is directed to read existing documentation files in Step 3 of the Update Process using the command
cat .trellis/spec/<category>/<file>.mdto understand the current state before making updates. - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the agent to use when processing the content of these files.
- Capability inventory: The skill's primary capabilities involve reading local files via
catand generating text-based documentation updates. - Sanitization: There is no explicit mechanism described to sanitize, validate, or filter the content retrieved from the files before it is processed by the agent.
Audit Metadata