chous
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads the
chouspackage from the public NPM registry usingnpxornpm install -g. This behavior is expected as it is the core tool the skill is designed to manage. - [COMMAND_EXECUTION]: The skill executes shell commands including
npx chous,npm install, andripgrep(rg) to inspect the repository environment and enforce file-naming and layout policies. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the repository's file system to determine its actions. Ingestion points: The contents of
package.json,.chousconfiguration files, and the repository's directory structure (e.g.,ClientApp/,src/). Boundary markers: There are no explicit instructions or delimiters to prevent the agent from following commands that might be embedded within these files. Capability inventory: The skill possesses the ability to modify repository files and execute arbitrary shell commands via thechousCLI or standard Node tooling. Sanitization: No explicit sanitization or validation of the configuration file content is performed before processing.
Audit Metadata