content-repurpose

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external content (such as blog posts and transcripts), which serves as an ingestion point for indirect prompt injection.\n
  • Ingestion points: Stage 1 in SKILL.md and the instruction patterns in the patterns/ directory (e.g., patterns/blog-to-thread.md) instruct the agent to analyze user-provided source material.\n
  • Boundary markers: The instructions do not define boundary markers or provide 'ignore embedded instructions' warnings for the data being processed.\n
  • Capability inventory: The skill relies on the agent's standard text processing and file handling tools; it does not contain explicit dangerous commands like eval or sudo.\n
  • Sanitization: No sanitization or escaping of the external content is performed before the agent processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 03:25 AM
Security Audit — agent-trust-hub — content-repurpose