qa-flaky-governance
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources such as Playwright trace files and CI failure reports to classify and reproduce tests.
- Ingestion points: Playwright trace files, CI history, and Vitest junit/json reports are accessed from the filesystem.
- Boundary markers: The instructions do not specify any delimiters or safety markers to prevent the agent from interpreting instructions embedded within failure messages or test names.
- Capability inventory: The skill uses the
Bashtool to execute dynamically generated reproduction commands (e.g.,npx playwright test --grep '...'). - Sanitization: There are no explicit requirements to sanitize test names or metadata before they are interpolated into shell commands, which could allow an attacker to trigger arbitrary command execution if a test name contains shell metacharacters.
Audit Metadata