z-qa-analyst
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the external environment (such as requirements documents and source code) and possesses capabilities to interact with the system via test runners, which establishes a surface for indirect prompt injection.
- Ingestion points: The skill is instructed to read scoped requirements, public interfaces, existing tests, and coverage evidence files as part of its inspection process.
- Boundary markers: There are no explicit delimiters or instructions to treat ingested external data as untrusted or to ignore any embedded instructions within those files.
- Capability inventory: The skill is authorized to 'Run or read current applicable coverage evidence through the bounded project wrapper', which involves executing command-line test suites and tools.
- Sanitization: No sanitization, escaping, or validation steps are defined for the content read from external project files or requirements.
Audit Metadata