skills/metroscope-dev/skills/caveman/Gen Agent Trust Hub

caveman

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of stylistic instructions for the AI agent and does not include any executable code, scripts, or external dependencies.
  • [PROMPT_INJECTION]: The persistence instructions ('ACTIVE EVERY RESPONSE once triggered') are designed to maintain stylistic consistency within the conversation and do not attempt to override safety protocols or system-level constraints.
  • [DATA_EXFILTRATION]: There are no commands or instructions that access sensitive local files or perform network requests to external domains.
  • [COMMAND_EXECUTION]: The skill uses the 'disable-model-invocation' flag, which restricts the agent's ability to call external tools or models, further reducing the attack surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 04:24 PM
Security Audit — agent-trust-hub — caveman