Volcengine Agent Identity

UserPool login, TIP token, credential hosting, and tool risk approval. Activate when user needs to check identity (whoami/status), log in, list/add credentia...

This skill is coherent for identity and credential management and does not request unrelated secrets or installs. Before enabling it, consider: 1) Only enable the plugin if you need agent-hosted credentials or OIDC/TIP flows. 2) Review where credentials will be stored and who can access them; ensure storage is encrypted and access-audited. 3) Pay attention to bindings: binding a provider to an env var lets other tools receive those secrets — restrict which tools/agents can use injected env vars. 4) Keep authz.requireRiskApproval enabled (and avoid allowing the agent to self-approve) so high-risk commands require explicit user approval. 5) Monitor approval logs and periodically review providers and bindings. If you are uncomfortable with an agent having the ability to inject credentials into tool invocations, do not enable this plugin.

Type: OpenClaw Skill Name: volcengine-agent-identity Version: 0.2.1 The skill is classified as suspicious due to a high-risk vulnerability in the `identity_fetch` tool. Specifically, the `returnValue: true` parameter allows the AI agent to retrieve the raw credential string directly. If an attacker can craft a prompt to trick the agent into calling `identity_fetch` with this parameter for an existing credential, the agent would gain access to the sensitive credential, enabling potential exfiltration. While the skill includes security features like risk checking and explicit instructions against agent self-approval, this specific capability presents a significant attack surface for credential theft via prompt injection.