module-use-case
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (
node,npm) to retrieve project metadata frompackage.jsonand run unit tests. These operations are essential for the skill's primary purpose of code verification and are performed within the local development environment.\n- [PROMPT_INJECTION]: The skill ingests data from local project files (e.g., source code and configuration) to maintain architectural consistency. This represents a surface for indirect prompt injection should the local project files be compromised, which is a standard risk for context-aware development tools.\n - Ingestion points: Local project configuration and source files (
package.json, existing use cases).\n - Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore embedded commands in the files it reads.\n
- Capability inventory: File system write access and shell command execution (
npm run test).\n - Sanitization: The skill does not explicitly describe sanitizing data extracted from project files before passing it to the shell.
Audit Metadata