qa-quality-perspective
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a constrained workflow for QA analysis across different stages of software development. It uses internal prompt files for logic and does not execute external scripts or binaries. Findings indicate the skill adheres to best practices by instructing the agent to differentiate between supplied evidence and inference.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze external data such as requirements and code PRs, which is a common vector for indirect prompt injection. However, the instructions provide strong boundary markers, requiring the agent to separate facts from inference and to report missing evidence. Furthermore, the skill does not possess capabilities (like file writes or network access) that could be exploited through such injections.
Audit Metadata