report
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using
npx playwrightandcurlto perform test runs and send notifications. These commands are consistent with the skill's stated purpose and standard development workflows. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external test reports, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads JSON output generated by
npx playwright testas described in Step 2 of SKILL.md. - Boundary markers: There are no specific delimiters or instructions to the agent to ignore or treat test names and error messages as untrusted content.
- Capability inventory: The skill has the capability to write markdown files to the filesystem and perform network requests via
curl. - Sanitization: The skill does not specify any sanitization, validation, or escaping mechanisms for the test data before it is interpolated into the markdown summary or the Slack payload.
Audit Metadata