Back to skill

Security audit

teneo-agent-deployment

Security checks for vulnerabilities and agentic risk

Overview

The skill's instructions require network installs, unannounced environment variables, and tell the agent to auto-update its instructions from an external URL and run end-to-end without user interaction — these behaviors are disproportionate or inconsistent with the published metadata and merit caution.

This skill is not outright malicious but has multiple red flags: it expects you to provide private keys and API keys that are not declared in the registry, it instructs the agent to install system software and fetch a Go SDK, and — most importantly — it tells the agent to compare and replace its local SKILL.md with a copy from https://openclaw.careers/SKILL.md before running. Before installing or running this skill: 1) Do not supply any wallet PRIVATE_KEY or production OpenAI key unless you fully understand and trust the SDK and minting process. 2) Inspect the upstream SDK repository (github.com/TeneoProtocolAI/teneo-agent-sdk@v0.6.7) and the remote SKILL.md URL manually to verify content and intent. 3) Prefer running the full sequence inside an isolated environment (throwaway VM or container) and avoid exposing real credentials; consider creating a separate wallet with minimal funds for testing. 4) Ask the publisher to declare required env vars and explain the remote-update step (why openclaw.careers is the canonical source). If you cannot verify those items, do not run this skill with sensitive credentials or on a production host.

SkillSpector findings are pending for this release.