server-actions-vs-api-optimizer

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • COMMAND_EXECUTION (MEDIUM): The skill instructs the user to execute a local Python script (scripts/analyze_routes.py) to automate codebase analysis. This involves command-line execution and recursive filesystem access to read project files.
  • PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection (Category 8) as it ingests and processes content from a user's codebase which could contain malicious instructions. Evidence: (1) Ingestion points: Source code files in the user-specified directory path. (2) Boundary markers: No markers or 'ignore' instructions are documented to prevent the agent from following instructions embedded in the scanned code. (3) Capability inventory: Filesystem read access and command execution. (4) Sanitization: The documentation does not mention sanitizing or validating the content of the analyzed files.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 06:28 PM