comment-funnel

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: No malicious patterns or unauthorized behaviors were detected. The skill is designed to manage Instagram DM automation using the vendor's platform and official Instagram Private Replies API.\n- [EXTERNAL_DOWNLOADS]: The README provides installation instructions using npx skills add Upload-Post/upload-post-comment-funnel, which targets the author's official skill distribution channel.\n- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it reads and processes untrusted user-generated content from Instagram comments.\n
  • Ingestion points: Data enters the context via the GET /uploadposts/comments endpoint in SKILL.md.\n
  • Boundary markers: The skill does not define specific delimiters or instructions to encapsulate untrusted data when the agent evaluates comment content.\n
  • Capability inventory: The agent has the ability to send DMs and configure background monitoring tasks based on processed comment data.\n
  • Sanitization: There is no instruction to sanitize or filter comment text before the agent performs semantic intent analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 10:41 PM