clojure-write
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a local script
./bin/magefor REPL interaction and code evaluation. This is a common practice for project-specific task runners and build tools. - [REMOTE_CODE_EXECUTION]: Provides instructions for dynamic execution of Clojure code via
clojure_evaland REPL sessions. This is the primary and intended purpose of the development skill. - [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests and evaluates Clojure source code. Ingestion points: Clojure source files and REPL inputs. Boundary markers: None specified. Capability inventory: Evaluation of Clojure code via
clojure_evaland./bin/mage. Sanitization: None specified beyond standard agent logic.
Audit Metadata