instagram-comments
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves user-generated content via the
instagram_comments_listtool. Since this data (comments) is untrusted and processed by the agent to perform actions like replying or hiding, it represents a standard indirect prompt injection surface where a malicious comment could attempt to influence the agent's logic.
Audit Metadata