instagram-automation
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Instagram comments and user-supplied captions in SKILL.md, which can be exploited for indirect prompt injection attacks.\n
- Ingestion points: Instagram media comments (INSTAGRAM_GET_IG_MEDIA_COMMENTS), user-provided image_url, video_url, and caption strings.\n
- Boundary markers: There are no instructions in SKILL.md for using delimiters or boundary markers to isolate external data from instructions.\n
- Capability inventory: The skill possesses write capabilities including publishing posts and carousels (INSTAGRAM_CREATE_POST, INSTAGRAM_POST_IG_USER_MEDIA_PUBLISH) in SKILL.md, as well as read capabilities for user information and insights.\n
- Sanitization: No sanitization or filtering logic is specified in SKILL.md for the ingested content.\n- [EXTERNAL_DOWNLOADS]: The skill configuration in SKILL.md requires the addition of an external MCP server endpoint (https://rube.app/mcp) to enable its functionality.
Audit Metadata