cowork-medical-bill-auditor

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data in the form of medical bills and EOBs, which creates a surface for indirect prompt injection attacks. 1. Ingestion points: Medical documents read via the Read tool. 2. Boundary markers: The instructions do not define delimiters to separate document content from agent instructions. 3. Capability inventory: The skill utilizes tools with high capability, including Bash, Write, and WebSearch. 4. Sanitization: No filtering or validation of document content is mentioned.
  • [NO_CODE]: The skill consists of Markdown instructions and YAML configuration only, containing no external scripts or executables.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 06:05 PM
Security Audit — agent-trust-hub — cowork-medical-bill-auditor