cy-create-techspec

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted data from external sources, specifically the PRD file (_prd.md) and the project's codebase. Maliciously crafted content within these files could potentially influence the agent's reasoning or the technical designs it generates.\n
  • Ingestion points: Business requirements and technical context are gathered by reading the _prd.md file and performing codebase exploration as described in the Workflow section of SKILL.md.\n
  • Boundary markers: The instructions do not define explicit delimiters or security warnings to isolate ingested data from the agent's core instructions.\n
  • Capability inventory: The skill involves reading and writing files within the .compozy directory and utilizing agent tools for codebase analysis.\n
  • Sanitization: The workflow does not include any validation or sanitization steps for the content extracted from the PRD or analyzed source code.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 12:15 AM