pw-locator-fixer
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Playwright test scripts and Page Objects as input. It lacks explicit boundary markers or sanitization logic to handle potentially malicious instructions embedded in the analyzed code.
- [COMMAND_EXECUTION]: The workflow includes executing shell commands such as
npx playwright test <file>andnpx playwright codegen <url>. If the input file provided for analysis contains malicious code, it could be executed in the local environment during verification. - Ingestion points: The skill ingests code from files provided by the user in SKILL.md.
- Boundary markers: There are no specific delimiters or instructions to ignore embedded commands in the source code.
- Capability inventory: The agent can execute local CLI tools (Playwright) and perform file-system writes (patching code).
- Sanitization: No sanitization or verification of the input code is performed prior to execution or patching.
Audit Metadata