project-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external codebases by reading manifest files, source code, and documentation (READMEs). This creates a surface where malicious instructions embedded in the analyzed project could influence the agent's behavior.
- Ingestion points: manifest files (package.json, requirements.txt, etc.), source files (imports and design patterns), and documentation (README.md).
- Boundary markers: The instructions lack specific delimiters or instructions for the agent to ignore potentially malicious content within analyzed files.
- Capability inventory: The skill utilizes Read, Glob, Grep, and Bash tools, and scripts/main.cjs can spawn subprocesses.
- Sanitization: No explicit sanitization or filtering of ingested file content is defined in the execution process.
- [COMMAND_EXECUTION]: The skill's instructions (Steps 6, 7, and 9) involve running system commands such as npm audit, npm outdated, and potentially project-specific linters or test scripts. While these are appropriate for the skill's purpose, they involve executing code from the environment.
- [DYNAMIC_EXECUTION]: The scripts/main.cjs file uses child_process.spawn to execute an external JavaScript file (analyzer.mjs). This is a standard execution pattern for this type of tool but represents dynamic loading of executable content.
Audit Metadata