fix-my-opening-line

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and rewrite user-supplied text for social media posts, creating a potential surface for indirect prompt injection. \n
  • Ingestion points: Processes user-provided post content during the diagnostic and rewrite steps. \n
  • Boundary markers: None identified; user content is processed directly based on the provided framework. \n
  • Capability inventory: Mentions integration with tools like suggest_hooks, score_voice_match, and improve_post. \n
  • Sanitization: No input sanitization or validation steps are described for handling external content. \n- [NO_CODE]: The skill consists entirely of instructional text and does not include any executable scripts or configuration files. \n- [SAFE]: The inclusion of a link to 'voicemoat.com' and mentions of its specialized tools are legitimate references to the skill's intended service and do not represent a security threat.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 07:23 AM