api-test-executor
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing untrusted external data which constitutes a potential attack surface.
- Ingestion points: The
test_plananddata_seedsinputs in SKILL.md serve as primary data sources that could be weaponized with malicious instructions. - Boundary markers: There are no instructions for using delimiters or special markers to isolate the test plan content from the agent's core instructions.
- Capability inventory: The agent is authorized to perform network requests and process API responses, which can be manipulated via a poisoned plan.
- Sanitization: The skill lacks explicit guidance for the agent to validate or sanitize the content of the plans or data seeds before execution.
- [NO_CODE]: The skill bundle consists exclusively of markdown instructions and metadata; no executable scripts, binaries, or configuration files are present for analysis.
Audit Metadata