swe-review-architecture-project

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes a shell command (find) to list the local project directory structure for analysis. This is a standard discovery operation used to understand the project layout.
  • [PROMPT_INJECTION]: The skill processes external data from project files (e.g., README.md, package.json) to generate summaries, which creates a surface for indirect prompt injection.
  • Ingestion points: Reads local project files including README.md and various dependency manifest files across multiple ecosystems.
  • Boundary markers: None present; the agent is instructed to read the files directly.
  • Capability inventory: Limited to file reading and directory discovery via shell commands.
  • Sanitization: No explicit sanitization of input data from files is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 02:39 AM
Security Audit — agent-trust-hub — swe-review-architecture-project