pw-api-tester
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external content such as OpenAPI specifications, endpoint contracts, or pasted snippets from users. This represents an indirect prompt injection surface where malicious instructions could be embedded in the data to manipulate the generated test code.
- Ingestion points: The workflow in
SKILL.mddescribes extracting contracts from user-provided endpoints and snippets. - Boundary markers: The instructions lack specific guidance for the model to treat external data as untrusted or to ignore embedded natural language instructions within those specs.
- Capability inventory: The skill identifies as a drafting tool; it generates TypeScript code for use with Playwright but does not have the capability to execute the generated code, perform network operations, or write to the file system itself.
- Sanitization: There are no instructions for validating or sanitizing the input data before processing.
Audit Metadata