skills/shipshitdev/skills/prd-writer/Gen Agent Trust Hub

prd-writer

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security threats or malicious patterns were detected. The skill consists of instructional markdown for requirement engineering.
  • [PROMPT_INJECTION]: The skill facilitates reading content from external issue trackers, which serves as a potential surface for indirect prompt injection if the source issues contain malicious instructions. This is an inherent property of the tool's intended workflow rather than a malicious instruction.
  • Ingestion points: External tracker issue bodies (SKILL.md).
  • Boundary markers: None explicitly defined for input; output follows a structured markdown template.
  • Capability inventory: Limited to interacting with project tracker APIs for reading and writing PRDs.
  • Sanitization: Relies on the agent's interpretation of the provided markdown structure.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 01:29 PM
Security Audit — agent-trust-hub — prd-writer