qe-shift-right-testing
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill defines a workflow for indirect prompt injection by processing external data to influence agent actions.
- Ingestion points: The
Incident Replayfunctionality inSKILL.mdingests production incident metadata (id, type, conditions) to drive the automated generation of regression tests. - Boundary markers: There are no explicit delimiters or 'ignore embedded instructions' warnings surrounding the interpolation of incident data into the agent's task context.
- Capability inventory: The skill utilizes
Taskcalls andFleetManager.coordinateto trigger failure injections, performance monitoring, and code generation across multiple agent roles. - Sanitization: The skill lacks instructions for sanitizing or validating incident data before it is processed by the
qe-production-intelligenceagent to create new tests.
Audit Metadata