v1.0.0

One API key. 70+ models. Route requests to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more.

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 5:33 AM.

Analysis

This skill appears to do what it says: route user-supplied prompts to an external LLM gateway using an AISA API key.

GuidanceThis looks purpose-aligned for a unified LLM routing skill. Before installing, confirm you trust the AIsa gateway, use a scoped or dedicated API key if possible, watch for costs, and avoid sending sensitive data unless you are comfortable with the gateway and downstream model providers receiving it.

Findings (2)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Permission boundary

Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.

Identity and Privilege Abuse

SeverityLowConfidenceHighStatusNote

scripts/llm_router_client.py

self.api_key = api_key or os.environ.get("AISA_API_KEY")

The client reads an API key from the environment and uses it for authenticated requests. This is expected for an LLM gateway, but it is still credential use that users should understand.

User impactAnyone using the skill must provide an AISA API key, and requests may consume quota or incur charges on that account.

RecommendationUse a dedicated API key with appropriate limits, monitor usage, and avoid sharing the key in prompts, logs, or screenshots.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Insecure Inter-Agent Communication

SeverityLowConfidenceHighStatusNote

scripts/llm_router_client.py

BASE_URL = "https://api.aisa.one/v1"

The skill sends chat messages, model comparison prompts, and image-analysis requests to an external gateway endpoint. This matches the stated purpose, but user data leaves the local environment.

User impactPrompts, conversation content, function schemas, and image URLs supplied to the skill may be transmitted to the AIsa gateway and routed to downstream model providers.

RecommendationDo not send secrets, regulated data, or private files unless the gateway’s privacy, retention, and provider-routing policies meet your needs.