cw-bluf

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting and analyzing untrusted user content (articles, essays, and memos), which is a prerequisite for indirect prompt injection attacks. Although the skill lacks execution capabilities that would make such an attack dangerous, it does not implement specific sanitization for the input data.\n
  • Ingestion points: The skill reads 'supplied writing' and 'artifacts' from the user context as described in SKILL.md.\n
  • Boundary markers: The skill does not define specific isolation markers or instructions to ignore embedded commands within the processed text.\n
  • Capability inventory: The skill is restricted to text analysis and revision; it lacks tools for network communication, file system modification, or shell command execution.\n
  • Sanitization: Input text is processed as-is without filtering for potentially malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 06:43 PM
Security Audit — agent-trust-hub — cw-bluf