copy-editing

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process untrusted text provided by users for editing and to read local context files.
  • Ingestion points: User-supplied marketing copy and local configuration files such as ".agents/product-marketing.md" or ".claude/product-marketing.md" (SKILL.md).
  • Boundary markers: None defined for the input text.
  • Capability inventory: Text processing and local file reading.
  • Sanitization: No input sanitization logic is present, as the primary purpose is text refinement.
  • [NO_CODE]: The skill consists solely of markdown instructions and reference documents; no scripts or executable binaries are included.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 05:57 PM
Security Audit — agent-trust-hub — copy-editing