coinagerie-configure
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill instructs the agent to create and modify configuration files (
coinagerie.config.tsor variations) that are executed as code by the tool using thejitilibrary. This allows for arbitrary logic, including the use of Node.js built-in modules likenode:fsto read files, to be executed during the tool's initialization phase. - [INDIRECT_PROMPT_INJECTION]: The skill describes an attack surface where the tool ingests data from a workspace and performs actions based on it.
- Ingestion points: Scans files within the working directory based on
includeandexcludeglob patterns (e.g.,src/**,scripts/**). - Boundary markers: None described in the instructions to delimit or ignore instructions embedded in the scanned files.
- Capability inventory: The tool can write to the filesystem through the
outputsconfiguration, allowing it to modify files likeREADME.mdor generate new JSON glossaries. - Sanitization: No sanitization or validation of the scanned file content is mentioned before it is processed into glossary definitions.
- [COMMAND_EXECUTION]: The instructions reference running the
coinagerieCLI with various flags such as--write,--check, and--configto apply configurations and update project documentation.
Audit Metadata