configs-create

Pass

Audited by Gen Agent Trust Hub on Sep 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill documentation provides templates for curl and ldcli commands to manage AI configurations. These commands are directed at official LaunchDarkly API endpoints and CLI tools for administrative tasks.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests user input to generate instructions for AI agents.\n
  • Ingestion points: User-provided text for AI instructions and messages in SKILL.md.\n
  • Boundary markers: None identified.\n
  • Capability inventory: MCP tools for creating and updating configurations, including setup-ai-config and create-ai-config-variation in SKILL.md.\n
  • Sanitization: None specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 29, 2026, 07:41 AM