trellis-check
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection vulnerability surface because it processes untrusted or external file content within the workspace.
- Ingestion points: Processes project artifacts including
prd.md,design.md,implement.md, and spec documentation under.trellis/spec/during the context gathering step. - Boundary markers: Absent; the instructions do not specify encapsulation delimiters or instructions to ignore embedded prompts within the files being read.
- Capability inventory: Possesses capabilities to execute local commands including
git status,git diff,grep,cat, and a project-specific script viapython3 ./.trellis/scripts/get_context.py. - Sanitization: Absent; content from the markdown specifications is parsed directly without preprocessing or escaping.
Audit Metadata