gen-specs-as-issues
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of high-level instructions for a Product Manager workflow. It does not include executable code, remote script downloads, or requests for sensitive system access.
- [PROMPT_INJECTION]: The skill defines a workflow where the agent reads and analyzes external project data (README, source code, tests) to generate content for GitHub issues. This process inherently exposes the agent to an indirect prompt injection surface if the processed data contains malicious instructions. However, this surface is essential to the skill's primary function and no adversarial patterns were detected within the workflow itself. • Ingestion points: Phase 1 instructions to read README.md and core project modules. • Boundary markers: None specified to separate processed content from agent instructions. • Capability inventory: Creating GitHub issues based on analysis (SKILL.md Phase 5). • Sanitization: No explicit content validation or sanitization is described.
Audit Metadata