clojure-symbols
Fail
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions include the use of
sudoto install packages on Arch Linux systems, which represents a privilege escalation risk if executed by an agent. - [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and execute a shell script directly from a remote GitHub repository (
raw.githubusercontent.com/clj-kondo/clj-kondo) which is not on the trusted vendors list. - [REMOTE_CODE_EXECUTION]: The skill relies on the
clj-nrepl-evaltool to evaluate arbitrary Clojure code on a running nREPL server, providing a mechanism for full code execution in the target environment. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection. Ingestion points: The agent reads Clojure source files using the
Readtool. Boundary markers: No boundary markers or instructions to ignore embedded commands are used when processing file content. Capability inventory: The agent has access toBash(for running analysis and REPL commands) andEdit(for modifying files) tools. Sanitization: The skill does not provide methods for sanitizing symbol names or file contents before they are interpolated into shell commands or REPL evaluation strings.
Recommendations
- AI detected serious security threats
Audit Metadata