metronome-create-contract

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external order forms to populate API requests, presenting a surface for indirect instructions. Ingestion points: Signed order form terms extracted in Step 1 (SKILL.md). Boundary markers: Absent; the instructions do not specify delimiters to separate untrusted data from the prompt. Capability inventory: Authenticated API access to create and list contracts and retrieve invoice details (SKILL.md). Sanitization: The skill performs unit conversions for amounts and formatting for dates but lacks specific validation or sanitization for descriptive string fields.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 11:36 PM
Security Audit — agent-trust-hub — metronome-create-contract