shadow-cljs-debug

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill specifies commands to manage the local development environment, such as clearing the build cache using rm -rf .shadow-cljs .cpcache and triggering the compiler with npx shadow-cljs compile. These are standard developer operations within the context of Shadow-CLJS.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it is designed to analyze external project configuration files and compiler error logs which may contain untrusted data.
  • Ingestion points: Reads content from shadow-cljs.edn, deps.edn, package.json, and dynamic compiler error messages.
  • Boundary markers: No specific delimiters are used to isolate untrusted data during processing.
  • Capability inventory: The agent can delete local cache directories and execute the shadow-cljs binary via npx.
  • Sanitization: No explicit sanitization or validation of the input data is mentioned before processing or inclusion in instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 02:57 AM