declare-session-mode

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely composed of documentation and prompt templates. It does not contain any executable code, shell scripts, or automation logic that could perform actions on the host system or network.- [PROMPT_INJECTION]: The content is designed to establish explicit boundaries and safety constraints for the AI agent (e.g., 'Stop Line', 'Authorization Scope'). It does not contain any patterns typical of malicious prompt injection or instruction overrides.- [DATA_EXFILTRATION]: There are no network-related commands (curl, wget, etc.) or access to sensitive local file paths.- [EXTERNAL_DOWNLOADS]: The skill does not define or request any external packages or remote scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 07:13 AM
Security Audit — agent-trust-hub — declare-session-mode