fix-failed-posts

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses well-defined internal tools like list_posts_advanced, get_account_health, and retry_failed_post to perform its stated functions. No external network requests to unverified domains or remote code executions were detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from social media platforms (post results and error messages) which represents a potential injection surface.
  • Ingestion points: Data enters the agent context through the list_posts_advanced and get_post_results tools defined in SKILL.md.
  • Boundary markers: No specific delimiters or safety warnings for handling external content are provided in the instructions.
  • Capability inventory: The skill has the ability to write/modify data using update_post and trigger actions via retry_failed_post and create_reconnect_link.
  • Sanitization: No explicit sanitization or validation steps for the ingested post content are mentioned in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 06:54 AM