awslabs-aws-api-mcp-server-suggest-aws-commands

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill interacts with an MCP server associated with AWS Labs, which is a well-known and trusted service.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes untrusted user data to generate command suggestions.
  • Ingestion points: The 'query' argument in SKILL.md accepts up to 2000 characters of user-supplied natural language.
  • Boundary markers: There are no explicit delimiters or protective instructions defined to prevent the model from obeying instructions embedded within the user's query.
  • Capability inventory: The suggestions returned by this tool are intended to be reviewed and potentially executed by the agent, directly influencing future operations.
  • Sanitization: No input validation or sanitization of the natural language query is performed by the skill definition.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 08:28 PM