Optimize
Warn
Audited by Gen Agent Trust Hub on Aug 2, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to execute shell commands provided via the '--measure' and '--extract' arguments to calculate performance metrics, which allows for arbitrary system command execution.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. 1. Ingestion points: Reads and analyzes content from files specified in '--target' and '--files'. 2. Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore embedded commands or instructions within the target files. 3. Capability inventory: The skill has the capability to modify local files and execute shell commands based on its analysis. 4. Sanitization: No sanitization or filtering of the content from the target files is performed before processing.
- [EXTERNAL_DOWNLOADS]: The documentation provides examples using 'npx', which downloads and executes packages from the npm registry.
Audit Metadata