skill-lookup
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
search_skillsandget_skilltools to fetch AI skill metadata and file contents from the prompts.chat remote registry. This is an expected functional requirement for a skill manager.- [INDIRECT_PROMPT_INJECTION]: As the skill ingests and processes instructions from an external community-driven registry, it presents a surface for tool output poisoning (Vector 8c). Malicious content in the remote registry could potentially influence agent behavior or prompt the execution of unintended commands.
Audit Metadata