moai-tool-ast-grep
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Category 4: External Downloads (SAFE): The documentation references official installation methods for the
ast-greptool via Homebrew, npm, and Cargo. These point to official repositories and package registries which are considered trusted sources under the defined scope rules. - Category 2: Data Exposure & Exfiltration (SAFE): While the skill contains rules to detect hardcoded credentials (e.g.,
hardcoded-password-python), these are static patterns used for analysis of target code. No evidence of data exfiltration or hardcoded secrets belonging to the skill itself was found. - Category 8: Indirect Prompt Injection (LOW): The skill's primary function is to analyze user-provided source code. While the results of these scans are typically ingested by the agent, the analysis is performed via an external AST-based tool (
ast-grep), which does not execute the code or treat its contents as instructions. The risk of indirect injection via scan results is negligible and inherent to the tool's purpose. - Category 10: Dynamic Execution (SAFE): The skill includes rules to identify and warn against dynamic execution in target code (e.g.,
eval,os.system,subprocess.run). The skill itself does not utilize any dynamic execution or runtime code generation.
Audit Metadata