thirds
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides documentation and workflow instructions for the thirds.ai service, linking to official setup guides and related specialized skills under the vendor's GitHub organization. It correctly advises users to manage API keys using secure client-side secret stores rather than hardcoding them within the skill.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the rendering of documents from user-supplied HTML input. While this is the primary function of the tool, processing untrusted HTML content is a standard vector for indirect prompt injection, where embedded instructions in the data could attempt to influence agent behavior.
Audit Metadata