spec-driven-dev

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Prompt Injection] (SAFE): No instructions found that attempt to bypass safety filters or override core agent behavior. The content focuses exclusively on guiding a structured development workflow.
  • [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or access to sensitive file paths (e.g., SSH keys, AWS configs) were found. Network operations are absent.
  • [Remote Code Execution] (SAFE): No patterns of downloading or executing remote scripts (e.g., curl|bash) or packages were detected. Tool commands mentioned (e.g., /openspec) are provided as text examples for user interaction.
  • [Obfuscation] (SAFE): The file is written in clear markdown and YAML. No Base64, zero-width characters, or homoglyphs were used to hide malicious intent.
  • [Indirect Prompt Injection] (LOW): The skill identifies a potential surface where it may ingest local project data (e.g., CONTRIBUTING.md) to detect workflows. Evidence Chain: 1. Ingestion point: Reads local CONTRIBUTING.md. 2. Boundary markers: Absent in the markdown description. 3. Capability inventory: No destructive or network capabilities identified in the skill scripts. 4. Sanitization: N/A as it is a documentation guide. Risk is negligible due to the lack of exploitable tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:43 PM
Security Audit — agent-trust-hub — spec-driven-dev