artifact-evaluation-prep
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to perform smoke tests, including environment setup and executing quickstart commands defined within the user's local repository (documented in Step 5 ofSKILL.md). - [EXTERNAL_DOWNLOADS]: The skill employs
WebFetchandWebSearchto retrieve artifact evaluation guidelines and metadata from external venue websites and repositories (documented in Step 1 ofSKILL.md). - [PROMPT_INJECTION]: The skill processes untrusted data from external websites and user-provided project files (such as paper text), creating an indirect prompt injection surface where embedded instructions could potentially influence the agent's execution logic (documented as a risk surface in Category 8).
Audit Metadata