development-ai-tools

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists entirely of instructional markdown files providing best practices, security warnings, and checklists for AI-assisted software development. It does not contain executable code, external dependencies, or network operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for reviewing and diagnosing user-provided code (SKILL.md). While this creates an ingestion surface for untrusted content, the skill explicitly provides safety-focused reference files (references/sharp_edges.md) that instruct the agent to identify and correct security vulnerabilities, effectively acting as a defensive boundary.
  • Ingestion points: User-provided code and requests are processed for review and creation (SKILL.md).
  • Boundary markers: Instructions mandate grounding responses in reference files and correcting users based on validation rules (SKILL.md).
  • Capability inventory: No tool usage, subprocess calls, or network operations are present in the skill.
  • Sanitization: Not explicitly present, but reference files contain instructions to manually validate for common vulnerabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 02:23 AM
Security Audit — agent-trust-hub — development-ai-tools