coinagerie-collect
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill describes the usage of the
coinagerieCLI andnpx @coinagerie/clito scan codebases, generate glossaries, and perform checks. These tools are provided by the vendor and are used for the skill's primary purpose. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data by reading identifiers and file names from a codebase (ingestion point in scanned folders). It mitigates risk by ignoring comments, strings, and prose, and it utilizes
<!-- coinagerie:start -->and<!-- coinagerie:end -->as boundary markers for its generated output. The tool's capabilities include reading codebase contents and writing to specified glossary files.
Audit Metadata