analyze-yii2-project

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill analyzes external PHP codebases, which provides a surface for instructions embedded in code or comments to influence the analysis results.
  • Ingestion points: PHP controller, model, and migration files from the user-provided project path.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are mentioned in the workflow.
  • Capability inventory: Uses the codecompass utility for AST analysis, semantic indexing, and requirements extraction.
  • Sanitization: No sanitization or validation of the processed code content is specified.
  • Command Execution (SAFE): The skill utilizes local CLI commands (codecompass, composer, curl) consistent with its purpose of technical analysis. All network operations are restricted to localhost services (Weaviate, Ollama).
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:12 PM