instagram-comments
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted text from external Instagram comments, which could potentially contain instructions designed to trick the agent.
- Ingestion points: The
instagram_comments_listtool fetches comment data from external users as described in the workflow section ofSKILL.md. - Boundary markers: The instructions do not define clear delimiters or provide warnings for the agent to treat the text of the comments as untrusted data rather than instructions.
- Capability inventory: The skill enables the agent to take actions based on the ingested content, specifically via the
instagram_comments_replyandinstagram_comments_hidetools defined inSKILL.md. - Sanitization: The skill does not describe any validation or filtering mechanisms to sanitize the content of the comments before processing them.
Audit Metadata