site-md

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes project requirements and external site content, representing a potential surface for indirect prompt injection. * Ingestion points: Reads requirement documents and fetches site content via the web_fetch tool. * Boundary markers: No explicit delimiters or warnings are used to isolate untrusted input data. * Capability inventory: The skill utilizes the Write tool to create filesystem documentation and the web_fetch tool to read external data. * Sanitization: No sanitization or validation of input content is specified before the document is generated.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 08:30 PM
Security Audit — agent-trust-hub — site-md