qa-verification
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted data from external sources such as pull requests, bug reports, and tickets to define its testing scope and execution steps.
- Ingestion points: Metadata is retrieved via tools (MCP, API, CLI), authenticated local metadata, or direct user-provided ticket/PR details (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions embedded within the processed ticket/PR metadata.
- Capability inventory: The skill utilizes browser interaction, CLI command execution, HTTP request probes, and database/log access to perform verification (SKILL.md).
- Sanitization: No sanitization or validation protocols are defined for the external content before it is used to derive the QA scope and testing actions.
Audit Metadata