terms-generator

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs its stated function of analyzing a business model to generate legal templates. It includes a clear legal disclaimer and uses standard discovery tools (WebFetch, Read, Glob) to gather context.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external URLs and local codebases. While this presents a surface for indirect prompt injection, the impact is minimal as the output is restricted to generating a Markdown document (Terms of Service) and does not involve executing the ingested data.
  • Ingestion points: Target URLs via WebFetch (SKILL.md); Local files via Glob and Read (SKILL.md).
  • Boundary markers: None explicitly defined in the instructions to separate untrusted content from the agent prompt.
  • Capability inventory: Read, Write, Glob, Grep, WebFetch (SKILL.md).
  • Sanitization: No specific sanitization or filtering of external content is mentioned before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 05:49 AM
Security Audit — agent-trust-hub — terms-generator