trellis-update-spec
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates reading and updating documentation files within the
.trellis/spec/directory, which creates a potential surface for indirect prompt injection if those files contain malicious instructions. - Ingestion points: The skill reads existing documentation from the
.trellis/spec/path using thecatcommand to verify existing content before updates. - Boundary markers: There are no explicit instructions or delimiters provided to ensure the agent ignores or isolates instructions found within the spec files it processes.
- Capability inventory: The skill involves file read operations and instructions for the agent to modify documentation content based on task outcomes.
- Sanitization: The update process does not specify validation or sanitization of the content being read from or written to the documentation files.
Audit Metadata