session-help
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFE
Full Analysis
- Documentation (SAFE): The skill consists entirely of markdown documentation and instructions for the agent on how to display help content efficiently.
- No Code (SAFE): No executable scripts, shell commands, or programming logic are present in the skill definition. The logic provided in the 'Implementation' sections is pseudo-code for the agent's instructional guidance.
- Data Exposure (SAFE): While the skill mentions file paths like
.claude/sessions/and.claude/cache/, these are internal to the documented session system. No hardcoded credentials or exfiltration methods were found. - Prompt Injection (SAFE): No instructions attempting to bypass safety filters, extract system prompts, or override fundamental agent behavior were detected.
Audit Metadata