skills/jei-skappa/skills/discussion/Gen Agent Trust Hub

discussion

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill specifies a logical workflow for generating and managing decision logs within local project directories. It does not perform network operations, execute remote code, or access sensitive system files.
  • [PROMPT_INJECTION]: The 'Peer Framing' section explicitly instructs the agent to challenge user reasoning, disagree when evidence warrants, and avoid sycophancy. These instructions serve as a behavioral guardrail against simple prompt injection attempts by prioritizing evidence over user preference.
  • [DATA_EXFILTRATION]: File operations are restricted to project-specific paths such as docs/threads/ and discussions/. There are no instructions to read sensitive configuration files or transmit data to external servers.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 08:33 PM
Security Audit — agent-trust-hub — discussion