metronome-create-contract
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to extract data from external sources (signed order forms) to perform high-stakes operations such as creating billing contracts. This ingestion of untrusted data without proper isolation creates a potential for indirect prompt injection.
- Ingestion points: Instructions in Step 1 of
SKILL.mddirect the agent to collect terms from a 'signed order form'. - Boundary markers: There are no instructions defining delimiters or boundary markers (e.g., XML tags) to isolate the untrusted order form data from the agent's core instructions.
- Capability inventory: The skill has the ability to write to the financial system via the
POST /v1/contracts/createendpoint defined inSKILL.mdStep 4. - Sanitization: The skill lacks explicit validation or sanitization steps for the extracted data before it is interpolated into the API payload.
Audit Metadata