marketing-claims-review

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it ingests and processes untrusted marketing copy without adequate security controls.
  • Ingestion points: The skill accepts user-pasted content such as landing pages, emails, and ads (SKILL.md).
  • Boundary markers: Absent. The instructions do not define delimiters or tags to separate instructions from the untrusted copy being analyzed.
  • Capability inventory: The skill can write work products to the local file system at ~/.claude/plugins/config/claude-for-legal/product-legal/matters/<matter-slug>/ (SKILL.md).
  • Sanitization: Absent. There is no evidence of filtering or validation for the incoming marketing copy before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 03:57 PM
Security Audit — agent-trust-hub — marketing-claims-review