Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external Instagram users through comments and Direct Messages, which could potentially contain malicious instructions designed to influence the agent's actions.
- Ingestion points: Untrusted data enters the context through tools such as
instagram_comments_list,instagram_conversation_messages_get, andinstagram_messages_get(SKILL.md). - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" wrappers for the content retrieved from Instagram.
- Capability inventory: The skill grants the agent the ability to respond to users, delete comments, and publish new content based on its interpretation of the context (SKILL.md).
- Sanitization: No explicit sanitization or validation logic is defined within the skill for processing the text body of incoming messages or comments.
Audit Metadata