ash-mcp
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's documentation provides installation steps for the ASH MCP server using the official AWS Labs GitHub repository.
- [COMMAND_EXECUTION]: The skill executes various industry-standard security scanners on a local project directory via an MCP server interface to identify vulnerabilities.
- [INDIRECT_PROMPT_INJECTION]: The skill audits untrusted external source code, which could contain instructions intended to influence the agent. Ingestion points: Project source code identified by the source_dir path in SKILL.md. Boundary markers: No specific boundary delimiters are defined in the instructions. Capability inventory: Execution of multiple security analysis tools through the MCP server as documented in references/tool-reference.md. Sanitization: No input sanitization or output filtering for malicious instructions is specified.
Audit Metadata