linkedin-post-style

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted user data to generate LinkedIn posts and diagrams, creating an indirect injection surface. \n
  • Ingestion points: User-provided raw content and notes used for post drafting (SKILL.md). \n
  • Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands in the user-provided data. \n
  • Capability inventory: The skill can invoke external tools including md-to-pdf (which renders Mermaid diagrams), concept-to-image, and video generation skills such as remotion-video (SKILL.md). \n
  • Sanitization: No logic is present to sanitize or escape user content before processing it within the 5-act structure or passing it to visual companion skills.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 02:31 AM