clojure-namespace-architect
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves reading and processing data from untrusted local files.
- Ingestion points: The
audit_clojure_nstool is designed to read the content of.cljand.cljsfiles to identify and extract namespace declarations. - Boundary markers: The skill does not define specific delimiters or instructions for the agent to distinguish between the namespace declaration and other potentially malicious instructions embedded in comments or strings within the source files.
- Capability inventory: The skill empowers the agent to perform file system operations including moving files (
mv), creating directories (mkdir), and modifying file content to update namespace symbols. - Sanitization: No sanitization or validation logic is specified for the content read from the files before it is processed by the agent.
Audit Metadata