kim-decision
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a high-level instruction set for decision reasoning and does not contain malicious code, obfuscated payloads, or credential theft mechanisms.
- [EXTERNAL_DOWNLOADS]: The skill includes instructions for the agent to use standard tools like web search to verify 'Evidence Tier' claims (e.g., in SKILL.md and references/gates.md). These are legitimate uses of agent capabilities for fact-checking.
- [COMMAND_EXECUTION]: The README.md files contain shell commands intended for the user to manually install the skill into their local environment. These commands are transparent and perform standard file operations.
- [PROMPT_INJECTION]: The skill processes user-supplied 'Intent'. While this is a potential vector for indirect prompt injection, the skill mitigates this risk by requiring 'Evidence Gates' and 'Research Gates' that force the agent to verify claims against primary sources before acting on them.
Audit Metadata