ds-teaching-assistant

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access commands were found in the skill files.
  • [PROMPT_INJECTION]: The skill includes an 'Anti-Patterns' section that explicitly instructs the agent not to treat external content, logs, or tool outputs as trusted instructions. This provides a robust defense against indirect prompt injection by reinforcing the boundary between instructions and data.
  • [COMMAND_EXECUTION]: The documentation mentions a local Python script ('python scripts/export-gemini-skill.py') used for rebuilding the skill for specific platforms. This is an informational developer instruction for skill maintenance and does not represent a security risk during the skill's operational runtime.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 06:06 PM
Security Audit — agent-trust-hub — ds-teaching-assistant