content-repurposer

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill incorporates user-provided content into its prompt template, creating a surface for indirect prompt injection. \n
  • Ingestion points: The variable [PASTE YOUR ARTICLE/POST/TRANSCRIPT] in SKILL.md accepts arbitrary user text. \n
  • Boundary markers: The skill uses XML-style <original_content> tags to delimit user input. \n
  • Capability inventory: The skill has no tools or permissions for network access, file system operations, or command execution. \n
  • Sanitization: No input validation or filtering is implemented to prevent instruction override within the provided content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 07:56 PM
Security Audit — agent-trust-hub — content-repurposer