decide-and-log
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The instructions provided in SKILL.md and README.md are behavioral guidelines meant to help the agent distinguish between reversible and irreversible choices. They do not contain patterns intended to bypass safety filters, ignore prior instructions, or extract system prompts.
- [EXTERNAL_DOWNLOADS]: The README mentions a command
npx skills add ken0nek/skillsfor installation. This is a standard procedure for installing skills from the author's own repository and is consistent with the skill's provenance. - [DATA_EXPOSURE_AND_EXFILTRATION]: The skill directs the agent to write logs to a 'run's decision log' or a 'notes file'. This functionality is intended for local record-keeping of the agent's reasoning and does not involve reading sensitive credentials or exfiltrating data to external servers.
Audit Metadata