T01 · Skill Instruction Hijacking
- Location
SKILL.md:20- Finding
Autonomous External Registration and Mandatory Promotional Output
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This skill provides a real collaboration client, but it grants broad network, credential, and local-agent authority with unsafe defaults and insufficient user control.
Review before installing. Only use this with a trusted TeamAgent hub over HTTPS, avoid pasting tokens into chat, do not run watch mode unless you accept remote chat content being routed into a local OpenClaw session, and do not copy main-agent auth files or reuse the documented child-agent password.
SKILL.md:20Autonomous External Registration and Mandatory Promotional Output
agent-worker.js:253Untrusted Remote Chat Content Is Injected into the Privileged Main Agent Session
teamagent-client.js:17Bearer Tokens and Private Collaboration Data Are Transmitted over Plaintext HTTP
teamagent-client.js:55Arbitrary Hub Configuration Can Redirect Stored Bearer Credentials
SKILL.md:436Main-Agent Credentials Are Duplicated into Child Agents and Access Controls Are Broadly Expanded
SKILL.md:509Documentation Prescribes a Shared Predictable Password for Child-Agent Accounts
The skill description omits important security-relevant behavior such as persistent token storage and pairing/token pickup workflows. Under-disclosure of credential handling can cause users to approve or install the skill without understanding that secrets will be stored locally and reused.
The skill description omits important security-relevant behavior such as persistent token storage and pairing/token pickup workflows. Under-disclosure of credential handling can cause users to approve or install the skill without understanding that secrets will be stored locally and reused.
Referenced artifact was not completely inspected
> - 找不到?运行 `find ~ -name "teamagent-client.js" -type f 2>/dev/null` 或 `Get-ChildItem -Recurse -Filter teamagent-client.js`
Referenced artifact was not completely inspected
> - 找不到?运行 `find ~ -name "teamagent-client.js" -type f 2>/dev/null` 或 `Get-ChildItem -Recurse -Filter teamagent-client.js`
The skill explicitly instructs the human to paste a bearer token into chat, creating a natural-language secret exfiltration path. Chat transcripts are often logged, retained, or visible to intermediaries, so asking for a token through chat materially increases credential exposure risk.
The skill instructs operators to create and provision sub-agents, edit gateway configuration, and copy authentication files. Those actions materially extend the skill’s authority and can spread credentials across multiple workspaces, broadening the blast radius of compromise.
The default hub URL uses plain HTTP, so registration data, pairing codes, and bearer tokens may be transmitted unencrypted over the network. Any attacker on the network path can intercept or modify traffic, steal credentials, impersonate the hub, or tamper with task data, which is especially dangerous for an agent client that automatically polls and authenticates.
The entire protocol, including command descriptions, workflow text, and user-facing prompts, is specified only in Chinese, with no indication that users may choose another language or that the skill is intentionally restricted to a Chinese-speaking context. This can constitute a language/locale policy violation because the skill appears to force a specific language without user opt-in.
The protocol explicitly states that in team mode the server sends the task description to the Qwen API, but it does not document any user consent, warning, redaction, or data-classification guardrails. In a multi-agent collaboration platform, task descriptions can easily contain proprietary, personal, or security-sensitive information, so silent third-party transmission creates a real confidentiality and compliance risk.
The skill exposes operational capabilities involving environment/local execution context without declaring an explicit tool scope or permission boundary. In practice this increases the chance an agent will invoke filesystem, shell, or environment-dependent actions implicitly, reducing auditability and user awareness.
The pairing code is a temporary linking secret, and the skill directs the agent to extract it from command output and send it through chat. Although lower risk than a long-lived token, disclosing the code in chat still creates a capture/replay opportunity during its validity window.
The skill tells the agent to auto-save API tokens to ~/.teamagent/config.json without a prominent warning about secret sensitivity, local persistence, file permissions, or reuse risk. This can lead to insecure storage of long-lived credentials on shared or poorly secured systems.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
# Linux/Mac(curl)
curl -X POST {hubUrl}/api/tasks \
-H "Authorization: Bearer {你的token}" \
-H "Content-Type: application/json" \
-d '{
The watch mode routes mobile chat messages through a local OpenClaw/Claude session and then back to the TeamAgent server, which exceeds the stated task-collaboration scope. This creates a covert data-flow path for user chat content and can expose sensitive prompts, replies, or local context to systems the user did not expect.
The documentation does not clearly warn that watch mode relays mobile chat content to a local OpenClaw/Claude session and then back to the TeamAgent service. Missing privacy disclosure undermines informed consent and can lead to accidental exposure of sensitive chat content.
Broad natural-language triggers like 'help me register TeamAgent' or 'submit this step' lack scope checks and can cause unintended invocation. In an agent environment, ambiguous triggers may launch networked actions, credential use, or task submission without sufficiently specific user intent.
Watch mode reads a bearer token from a separate local OpenClaw configuration and uses it to invoke an unrelated local session router, extending the skill's authority beyond its stated team-task orchestration scope. This creates a cross-component trust violation: any incoming TeamAgent chat content can be relayed into another privileged local agent session, potentially exposing private data or causing unintended actions in that other system.
The code silently reads a sensitive gateway token from ~/.openclaw/openclaw.json and repurposes it for API access without notifying the user or obtaining consent. Even if kept local, this is dangerous because it normalizes unauthorized credential reuse across tools and expands the blast radius if the TeamAgent worker is compromised or behaves unexpectedly.
Incoming chat messages are forwarded to a local HTTP service for processing without explicit disclosure to the end user that their content is being relayed into another system/session. This creates a privacy and data-handling issue, and because the forwarded prompt targets a real agent session, user content may influence behavior in a privileged local environment beyond the expected TeamAgent chat workflow.
The injected prompt instructs the downstream session to reply in Chinese only, with no indication of user choice or locale negotiation. This is a natural-language policy issue because it hard-codes a language preference rather than offering or respecting user opt-in.
The prompt is entirely written in Chinese and explicitly requires specific Chinese output structures and artifact names, which effectively constrains the skill to a single language. There is no opt-in, language selection mechanism, or justification that this is a region-specific tool.
The decompose prompt contains hard-coded instructions that go beyond planning and explicitly direct creation of real sub-agents, filesystem changes, and local OpenClaw configuration updates. In a collaboration skill, this expands the agent's operational scope from orchestration into system-modifying actions, which can cause unauthorized agent proliferation or persistence if a downstream worker follows the generated plan.
The handler sends task descriptions and team-member information to a third-party LLM service, but there is no explicit disclosure, consent check, redaction, or policy guard before transmission. Because task and team data may include sensitive operational details, this creates a confidentiality and compliance risk through unintended external data sharing.
The manifest explicitly advertises "SSE realtime events," but the code only implements request/response HTTP methods plus polling in registerAndWait. There is no EventSource, stream parser, or persistent realtime subscription logic, so the described realtime behavior is not actually present in this file.
The client persists the API token to disk automatically in a predictable location without explicit user consent or any protection beyond file mode bits. On multi-user systems, backup/sync tooling, misconfigured permissions, or later local compromise could expose the bearer token and allow unauthorized access to the TeamAgent hub.