NYC

clojure-write

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill defines a workflow for ingesting and executing Clojure code, which presents an indirect prompt injection surface. \n- Ingestion points: Clojure and ClojureScript source files (SKILL.md). \n- Boundary markers: No explicit markers or ignore-instructions for untrusted content are provided. \n- Capability inventory: Execution of project code via ./bin/mage -repl (SKILL.md). \n- Sanitization: The skill does not describe any sanitization or verification of the code prior to REPL execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:33 PM