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, and Grep tools (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, and Write tools 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
Risk Level
SAFE
Analyzed
Jul 17, 2026, 06:05 PM
Security Audit — agent-trust-hub — cowork-contract-renewal-radar