feature-workflow

Pass

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructional guidelines for a documentation-driven workflow. It does not contain executable code, remote downloads, or credential exposure.
  • [PROMPT_INJECTION]: No attempts to bypass safety filters or override system instructions were detected. The skill defines a process for reading repository content (e.g., .plans/ and _docs/ directories), which represents a surface for indirect prompt injection. 1. Ingestion points: _docs/features//roadmap.md and .plans/.md. 2. Boundary markers: Absent. 3. Capability inventory: Local file read and write access. 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 5, 2026, 07:14 AM
Security Audit — agent-trust-hub — feature-workflow