api-testing
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, creating a potential surface for indirect prompt injection attacks.
- Ingestion points: Reads local API collection files (
*.request.yaml), environment files (-e), and captures real-time network traffic (postman application test). - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when the agent processes the content of these files or captured traffic.
- Capability inventory: The skill executes shell commands via the
postmanCLI tool, including the ability to run arbitrary user-provided commands using the--commandflag in theapplication testmodule. - Sanitization: There is no evidence of sanitization, validation, or filtering of the content retrieved from the external collection files or captured network data before it is processed by the agent.
Audit Metadata