skills/jeremylongshore/claude-code-plugins-plus-skills/openrouter-function-calling/Gen Agent Trust Hub
openrouter-function-calling
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill documentation and examples demonstrate communication with the OpenRouter API (https://openrouter.ai/api/v1). This is standard behavior for an API integration skill. The skill correctly instructs users to manage sensitive credentials via environment variables (OPENROUTER_API_KEY) rather than hardcoding them.
- [INDIRECT_PROMPT_INJECTION]: This skill implements an interface for automated tool execution, which inherently creates an indirect prompt injection surface.
- Ingestion points: Untrusted data enters the agent context via the
tool_callsfield in the model response (found inSKILL.mdandreferences/tool-router.md). - Boundary markers: The implementation uses a function-name whitelist (
TOOLSdictionary inSKILL.mdand theToolRouterregistration pattern) which prevents the model from calling arbitrary functions not explicitly defined by the developer. - Capability inventory: The skill environment is configured with wide Bash access (
Bash(python3:*)), and the provided logic executes code based on model-provided arguments. - Sanitization: The examples do not show explicit sanitization of tool arguments (e.g., shell escaping), relying on the developer to implement safe handlers for the registered functions.
Audit Metadata