soia-dev-draft-prd

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill documentation provides a command for installation using npx skills add, which is intended to be run by the user to set up the environment.
  • [EXTERNAL_DOWNLOADS]: The installation process involves downloading the skill package from the vendor's repository (soia-team/soia-open-dev-product-skills).
  • [PROMPT_INJECTION]: The skill processes external user-provided data such as interview summaries and requirement notes to generate PRDs, which is an inherent surface for indirect prompt injection.
  • Ingestion points: Ingests untrusted data through interview summaries and requirement notes as described in the workflow steps.
  • Boundary markers: The instructions include clear markers to distinguish between facts, inferences, and assumptions in the output document.
  • Capability inventory: The agent has the capability to write the resulting PRD draft to a file path specified by the user.
  • Sanitization: No explicit sanitization or filtering of input data is mentioned in the instruction set.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 04:43 PM
Security Audit — agent-trust-hub — soia-dev-draft-prd