competitor-alternatives
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from potentially untrusted external sources including scraped web pages, customer reviews, comments, and emails as specified in SKILL.md and references/skill-contract.md.
- [SAFE]: The skill explicitly mitigates injection risks by instructing the agent to treat all external content as untrusted evidence rather than instructions, a core invariant defined in the Unified Skill Contract (Rule 3).
- [SAFE]: The skill contract in references/skill-contract.md (Rule 4) prevents unauthorized persistence and privilege escalation by requiring explicit user authorization for any persistent writes or real-world side effects.
- [SAFE]: Secure configuration practices are promoted by instructions in references/connectors.md that advise against hardcoding API keys in skills or source control.
Audit Metadata