skills/stophobia/open-design/pm-spec/Gen Agent Trust Hub

pm-spec

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill serves as a template generator for product specifications. It uses standard HTML and CSS to render content and does not include any executable scripts, shell commands, or remote dependencies.
  • [SAFE]: The workflow requires reading 'DESIGN.md' from the project context. This access is limited to the agent's current workspace and is used exclusively for content generation; no exfiltration vectors or network operations are present.
  • [PROMPT_INJECTION]: The skill exhibits an ingestion surface for indirect prompt injection by processing external data from 'DESIGN.md'.
  • Ingestion points: 'DESIGN.md' (Workflow Step 1).
  • Boundary markers: No delimiters or specific warnings to ignore embedded instructions are present.
  • Capability inventory: The skill's output is restricted to generating text/html artifacts for display. It possesses no capabilities for file-system modification, network communication, or subprocess execution.
  • Sanitization: No explicit validation or escaping of input data is performed during the interpolation process.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 12:08 PM
Security Audit — agent-trust-hub — pm-spec