linkedin-post
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied ideas and external media to generate social media content, which presents a surface for potential instruction injection.
- Ingestion points: Processes user-provided descriptions ('idea'), photo URLs, and uploaded documents in the post-creation workflow (SKILL.md).
- Boundary markers: Includes a mandatory human-in-the-loop confirmation step ('Show the post exactly as it will go out... Nothing is published without a yes').
- Capability inventory: Possesses capabilities to perform network requests to postwire.io to publish or schedule content (post_to_social, schedule_post).
- Sanitization: Relies on manual user review of the generated content and configuration before the tool execution occurs.
- [EXTERNAL_DOWNLOADS]: Fetches account status, connection configuration, and additional instructions from the author's official domain (postwire.io). This represents standard communication with the vendor's infrastructure to support the skill's core functionality.
Audit Metadata