nango-function-builder

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Nango CLI for development workflows, specifically nango dryrun, nango deploy, and nango generate:tests. It also uses ls and pwd to verify the project's root directory. These are standard operations for managing Nango integrations.\n- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection because it consumes external API documentation and sample payloads to guide its code generation.\n
  • Ingestion points: External API reference URLs and sample responses are used as inputs in SKILL.md and the reference files.\n
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious instructions embedded in the external documentation.\n
  • Capability inventory: The skill possesses capabilities to modify the local file system (creating/updating actions and syncs) and execute CLI tools (nango, npm).\n
  • Sanitization: No automated sanitization or validation of the ingested external content is performed before it is used to generate executable code.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 09:44 PM