Skills
Navigate
skills/sergebulaev/linkedin-skills/linkedin-comment-drafter/Gen Agent Trust Hub

linkedin-comment-drafter

Pass

Audited by Gen Agent Trust Hub on Oct 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from LinkedIn posts and comments obtained via external tools.
  • Ingestion points: Data is fetched via lib.ApifyClient.fetch_post and fetch_post_comments, or through MCP connector tools as described in SKILL.md.
  • Boundary markers: The skill includes a dedicated 'Untrusted content' section that explicitly instructs the agent to treat fetched text as data and ignore any embedded instructions. It also references an external safety guideline ../../references/untrusted-content.md.
  • Capability inventory: The skill uses lib.publish and lib.repost to send content to LinkedIn after processing.
  • Sanitization: All generated drafts must pass through a manual approval step using lib.approval.render_approval_card, ensuring the user reviews and confirms the content before it is published.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 16, 2026, 07:42 PM