terms-of-service
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and analyze content from external, untrusted websites during the audit process.
- Ingestion points: Website HTML, footer links, registration forms, and server response headers identified in SKILL.md and references/rule.md.
- Boundary markers: The instructions do not define specific delimiters for separating audited site content from the agent's internal reasoning.
- Capability inventory: The skill itself is purely instructional and contains no executable scripts or subprocess calls.
- Sanitization: There are no explicit instructions for the agent to sanitize or escape data retrieved from the websites being checked.
- [NO_CODE]: The skill contains only markdown documentation and illustrative code snippets (HTML, TypeScript) for educational purposes. It does not include any executable scripts, configuration files, or build manifests that would run in the agent environment.
Audit Metadata