best-practices-chat

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: A test fixture in fixtures/agentic_eval.json includes a command to run a Python validation script (../../best-practices-skills/scripts/validate_skill.py). This is a local script execution intended for engineering standard compliance checks in a development environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines patterns for ingesting and displaying external compliance data which represents a theoretical attack surface.
  • Ingestion points: Data rendered in InlineEvidenceCase, InlineArtifact, and InlineFigure as specified in SKILL.md.
  • Boundary markers: No specific delimiters or warnings for embedded instructions are provided in the UX guidelines.
  • Capability inventory: The skill files contain no subprocess calls, file system writes, or network operations.
  • Sanitization: No data sanitization or filtering logic is described in the guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 06:00 PM
Security Audit — agent-trust-hub — best-practices-chat