pentest-api-deep
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external APIs, including OpenAPI/Swagger specifications, GraphQL schemas, and raw API responses. This data is used to dynamically guide the agent's next steps in the penetration testing workflow. 1. Ingestion points: API discovery via kiterunner_scan, GraphQL introspection via graphql_introspect, and response analysis during BFLA and mass assignment testing as described in SKILL.md and references/tools.md. 2. Boundary markers: The skill does not define specific boundary markers or instructions to ignore embedded prompts within the external API data. 3. Capability inventory: The skill utilizes network operations for API interaction and defines several functions for executing command-line security tools in references/tools.md. 4. Sanitization: There is no evidence of sanitization or validation of the external content before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill defines several tool wrappers in references/tools.md (e.g., kiterunner_scan, arjun_discover, grpcurl_call) that are intended to be executed by the agent to perform security scanning and fuzzing. These operations involve executing external binaries with parameters derived from the target API.
Audit Metadata