cs-feat-design
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a legitimate development workflow for creating feature designs and action checklists.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from local project files (roadmaps, requirements, and existing source code) without explicit boundary markers or sanitization. However, this is a standard risk for development-focused agents and the output is a design document intended for human review.
- Ingestion points:
SKILL.md(Flow Step 1 and 2) reads roadmap files, architecture docs, requirements, and existing code. - Boundary markers: Absent when reading external file content.
- Capability inventory: File system write access (
{slug}-design.md,{slug}-checklist.yaml) and execution of local project scripts (validate-yaml.py,search-yaml.py). - Sanitization: No explicit sanitization of ingested file content before processing.
Audit Metadata