qstack-encode-lessons-in-structure
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill is purely instructional and guides the agent on how to improve software architecture through types, schemas, and lints.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze user-provided code corrections and recurring mistakes.
- Ingestion points: User requests and historical code failures are used to identify patterns in
SKILL.md. - Boundary markers: The instructions explicitly state that analysis alone does not authorize edits, commits, or deployments, requiring a direct user request for implementation.
- Capability inventory: The skill does not define any internal tools or scripts; it relies on the agent's pre-existing capabilities.
- Sanitization: Not applicable as the skill provides guidelines for the agent's reasoning rather than automated data processing.
- [EXTERNAL_DOWNLOADS]: The skill contains a reference URL to a public GitHub repository (
github.com/cursor/plugins) for attribution purposes. This is a static markdown link and does not result in automated downloads or script execution.
Audit Metadata