api-simulation
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill documents legitimate use of the
postmanCLI for API simulation. It provides standard operational instructions for running background processes, managing dependencies, and inspecting logs. - [SAFE]: Includes explicit security guidance and warnings, such as advising against committing sensitive log files (
sim.ndjson) or API keys to version control systems. - [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for reading and updating architectural assumptions in natural language within YAML files (
.context.yaml). While this constitutes an ingestion surface for untrusted data, it is a core functional requirement of the tool and is handled as a structured data task. - Ingestion points: Processes configuration and context data from
postman/simulations/*.sim.yamlandpostman/simulations/*.context.yaml(SKILL.md, reference/context_file.md). - Boundary markers: None explicitly specified for natural language fields within the YAML schemas.
- Capability inventory: Executes shell commands using the
postmanCLI, manages background processes withpkill, and performs file system read/write operations (SKILL.md). - Sanitization: Relies on the structured nature of YAML and the
postmanCLI's own internal handling of these files.
Audit Metadata