NeoGriffin Security

Multi-chain security API designed exclusively for autonomous AI agents. Prompt injection detection (66 patterns, 95% accuracy), token scam scanning, tx simul...

This skill implements a plausible security API for autonomous agents, but proceed cautiously. Before installing or enabling it: - Ask the maintainer why NEOGRIFFIN_PAYMENT_WALLET is required as an environment variable and what the agent is expected to store in that env var (public address vs. any secret). Do not set any env var containing private keys or seed phrases. - Never send private keys, seed phrases, or signed private material to the API. Paid endpoints require a tx signature in X-Surge-TX — confirm the provider's claim about not storing full signatures and consider using ephemeral/test signatures first. - Test free endpoints with non-sensitive sample inputs to verify behavior and logs. Confirm that the payment wallet in SKILL.md matches the provider's published receiver address. - Be cautious about the instruction to POST "skill" or in-memory content — that can leak prompts, internal state, or other sensitive material; only send minimized, non-secret data. - Verify operator identity and reputation for api.neogriffin.dev (who runs it, privacy policy, SLA). If you plan to allow autonomous agent invocation that will call this service automatically, limit scope until you trust the provider. If the provider can explain the env-var usage and privacy guarantees in detail (and you audit a small trial), the skill could be usable. If those questions are unanswered, avoid granting it agent automation or sending any sensitive runtime data.

Type: OpenClaw Skill Name: neogriffin-security Version: 2.2.1 The neogriffin-security skill is a documentation-based bundle providing an AI agent with instructions to utilize a third-party security API (api.neogriffin.dev) for prompt injection detection, token auditing, and transaction simulation. It includes comprehensive documentation for 26 endpoints and explicitly instructs the agent to perform safety scans on all external inputs. The behavior is entirely consistent with its stated purpose as a security tool for autonomous agents, and no malicious code, deceptive instructions, or unauthorized data exfiltration patterns were identified.