content-repurposer

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes untrusted content from users or external sources.
  • Ingestion points: The instructions prompt the user to paste long-form content or provide a URL to be fetched via the Brave MCP tool.
  • Boundary markers: The skill lacks explicit boundary markers (e.g., XML tags or triple quotes) or system instructions to ignore commands embedded within the input data.
  • Capability inventory: Analysis of the skill body shows no evidence of dangerous capabilities such as file system writes, subprocess execution, or network exfiltration commands.
  • Sanitization: There is no documented validation or escaping mechanism for the ingested data before it is processed by the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 10:30 AM
Security Audit — agent-trust-hub — content-repurposer