write-tech-spec

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill instructions define a legitimate and safe development workflow. No patterns of credential theft, malicious code execution, persistence, or obfuscation were identified.
  • [INDIRECT_PROMPT_INJECTION]: The skill acts on external data by reading product specifications to generate technical plans, which constitutes a standard ingestion surface. (1) Ingestion points: Reads existing PRODUCT.md files and user-provided issue identifiers. (2) Boundary markers: None explicitly defined in the prompts. (3) Capability inventory: git CLI usage for commit tracking, GitHub and Linear API tools for issue management, and sub-agent parallelization via run_agents. (4) Sanitization: Not specified, though the output is focused on human-readable markdown documentation. The surface is considered low-risk given the skill's architectural purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 02:00 PM
Security Audit — agent-trust-hub — write-tech-spec