precision-mode
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill uses strong directives to override the agent's default output style, referring to itself as a "prompt injector" and "Prime Directive". It instructs the model to "Apply these rules to everything you generate" to eliminate verbosity, filler, and meta-commentary.
- Evidence: The skill explicitly commands the agent to lead with answers, drop filler phrases, and avoid restating user requests.
- Safety context: The instructions explicitly state: "Don't omit critical caveats (security warnings, breaking changes, data-loss risks)", ensuring that safety information is prioritized over brevity.
- [COMMAND_EXECUTION]: The README.md provides an installation command for the user to add the skill.
- Evidence:
npx skills@latest add amit-t/skills --skill precision-mode. - Context: This is a standard installation procedure for the platform and is initiated by the user, not executed automatically by the agent at runtime.
- [NO_CODE]: The skill is composed entirely of natural language instructions and contains no executable scripts (Python, JavaScript, etc.) or binary files.
Audit Metadata