vibe-techdesign

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of external project files.
  • Ingestion points: Content is read from docs/PRD-*.md and docs/research-*.txt to inform the technical design.
  • Boundary markers: The instructions lack explicit delimiters or 'ignore' commands to separate the provided documentation content from the agent's core instructions.
  • Capability inventory: The skill is permitted to use Read, Write, Glob, Grep, WebSearch, and AskUserQuestion tools.
  • Sanitization: There is no logic provided to sanitize or validate the content of the documents before they are used to generate the final technical design file.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 05:55 AM