write-x-thread-or-article

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data (such as blog posts, ideas, and media URLs) to generate social media content and execute tool actions.\n- Ingestion points: SKILL.md defines instructions for the agent to transform user-provided input into threads or articles and uses URLs for the upload_media_from_url tool.\n- Boundary markers: The instructions do not specify explicit delimiters or isolation instructions for user-provided content within the prompt interpolation, although the agent is instructed to show the final draft to the user.\n- Capability inventory: The skill possesses capabilities to write to external platforms via create_post and schedule_post, and can perform network operations via upload_media_from_url.\n- Sanitization: There is no mention of content sanitization, escaping, or validation of the user-provided data before it is processed or used in tool calls.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 06:54 AM