fix-failed-posts

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external platform error messages which could theoretically contain malicious instructions.
  • Ingestion points: The tools list_posts_advanced and get_post_results in SKILL.md retrieve status and error data from external social media platforms.
  • Boundary markers: No specific delimiters or instructions to ignore embedded content are present in the prompt templates when interpreting error reasons.
  • Capability inventory: The skill can perform state-changing actions based on external input, including update_post, retry_failed_post, and create_reconnect_link.
  • Sanitization: No explicit sanitization or validation of the error strings is mentioned before they are processed by the agent's logic to determine the next action.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 07:17 PM