cowork-contract-renewal-radar
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data (contract files in PDF and .docx format), making it susceptible to indirect prompt injection attacks where malicious text within a contract could influence the agent's behavior.
- Ingestion points: Files read from the local file system using
Read,Glob, andGreptools (SKILL.md). - Boundary markers: Absent. The instructions do not specify any delimiters or safety markers to separate document content from agent instructions.
- Capability inventory: The skill employs the
Bash,Read, andWritetools to perform analysis, manage files, and potentially interact with connected calendar services. - Sanitization: Absent. There is no instruction to validate or sanitize the text extracted from the contracts before it is used by the agent to compute dates or write reports.
- [NO_CODE]: The analyzed skill package does not contain any executable scripts, binaries, or source code files, relying solely on natural language instructions and built-in platform tools.
Audit Metadata