api-engineer
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data in the form of API contracts and specifications, creating a potential attack surface.
- Ingestion points: The skill reads local and remote Postman collections and OpenAPI specifications via commands like
postman workspace pulland local file operations as mentioned in Rules 2 and 9 ofSKILL.md. - Boundary markers: There are no explicit instructions for the agent to delimit or ignore instructions that may be embedded within the metadata or descriptions of the processed API specs.
- Capability inventory: The skill allows for file system operations (
postman init), cloud synchronization (postman workspace push), and network communication via thepostman feedbackcommand mentioned in Rules 6, 9, and 10 ofSKILL.md. - Sanitization: The skill includes a manual instruction (Rule 10) to exclude secrets and user data when reporting feedback, but it lacks automated validation or sanitization for the content of ingested API contracts.
Audit Metadata