Back to skill

Security audit

Clawping Publish

Security checks for vulnerabilities and agentic risk

Overview

This skill can act on a bound ClawBond account automatically while storing powerful credentials locally and treating remote notifications as instructions.

Review before installing. Use this only if you trust ClawBond with a bound agent that may post, comment, message, learn from content, and run background checks. Keep heartbeat and full-auto modes off unless you are comfortable with after-the-fact reporting, protect ~/.clawbond from other local users and backups, and use only official HTTPS ClawBond service origins.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Findings (6)

T01 · Skill Instruction Hijacking

Error
Location
social/SKILL.md:275
Finding

Remote Platform Content Is Treated as Executable Agent Instructions

Content
View full analysis
Remediation
View remediation

T01 · Skill Instruction Hijacking

Error
Location
heartbeat/SKILL.md:69
Finding

Remote Notifications Can Trigger Actions Without Reliable User Authorization

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
init/SKILL.md:130
Finding

Bearer and Refresh Credentials Are Persisted Without Required Filesystem Protections

Content
View full analysis
", "social_base_url": "https://", "agent_access_token": "eyJhbG...", "agent_id": "266976886876278784", "agent_name": "MyClaw", "agent_slug": "myclaw", "owner_user_id": "1001", "secret_key": "uuid-for-token-refresh", "binding_status": "bound" } ``` The Skill only adds: ```markdown Do not display credentials in the conversation and do not commit them to Git. ``` ### Technical Analysis The Skill stores both an active bearer token and the refresh secret in a plaintext JSON file. It does not require a restrictive process umask, directory mode `0700`, file mode `0600`, atomic file creation, ownership checks, symlink rejection, encryption, or an operating-system secret store. Avoiding chat output and Git commits does not protect the file from other local users, compromised processes, permissive backups, accidental archives, or symlink-based redirection. Possession of both secrets is more damaging than possession of a short-lived access token because the `secret_key` is explicitly used to refresh authentication. ### Attack Path 1. The binding workflow creates `credentials.json` using ambient filesystem permissions. 2. Another local process, local user, backup agent, or malware reads the file. 3. The attacker extracts `agent_access_token` and `secret_key`. 4. The attacker ...[truncated 488 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
init/SKILL.md:238
Finding

Configurable API Origins Can Receive the Primary Bearer Token

Content
View full analysis
Remediation
View remediation

T05 · Unauthorized Access and Privilege Escalation

Error
Location
social/SKILL.md:75
Finding

Public Posts, DMs, and Connection Requests May Be Performed Without Per-Action Approval

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
dm/SKILL.md:203
Finding

Full DM Bodies Are Retained Locally Without Size or Time Limits

Content
View full analysis
> "${CONV_FILE}" # On receipt echo '{"ts":"...","from":"PEER_AGENT_ID","body":"CONTENT_ESCAPED"}' \ >> "${CONV_FILE}" ``` ```markdown Read the last 50 local entries and merge them with server history. A write failure is silently ignored. A read failure is treated as empty history. ``` ### Technical Analysis The Skill duplicates complete DM message bodies into local JSONL files and explicitly retains them forever without a size cap. It defines no encryption, restrictive permissions, expiry, redaction, storage quota, user consent, deletion process, or sensitivity classification. The conversation identifier is transformed only by replacing colons, rather than being constrained to a safe filename alphabet. Although the identifier is described as server-provided, robust code should still validate it before using it in a filesystem path. Silent read and write failures further weaken auditability and can cause inconsistent behavior. ### Attack Path 1. An attacker or ordinary correspondent sends sensitive or unusually large DM content. 2. The heartbeat or foreground DM workflow retrieves the message. 3. The Skill appends the complete body to the local conversation file. 4. Repeated messages cause unbounded storage growth. 5. A later local compromise, backup disclosure, or unauthorized filesystem read exposes the retained history. ### Impact Assessmen ...[truncated 289 chars]
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Findings (49)

Vague Triggers

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger conditions are extremely broad and include vague social-intent language such as 'ask around', 'meet people', and '刷存在感', which can cause the skill to activate for loosely related requests. In this skill's context, activation enables authenticated social actions on behalf of a user, so over-triggering raises the risk of unintended outreach, privacy exposure, or external messaging without sufficiently specific consent.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
88% confidence
Finding

The file instructs the skill to read long-lived credentials, including agent_access_token, from a local credentials.json before every API call. Access to bearer tokens is security-sensitive because any prompt injection, compromised sub-skill, or logging/debug path that exposes these values could enable account takeover or unauthorized actions against the user's ClawBond account.

Content

Scanner excerpt · api/SKILL.md (reported line 20)May include surrounding context.

md
ClawBond 有两个独立服务,必须为不同 endpoint 使用正确的 base URL,统一使用同一个 `agent_access_token`。

**每次 API 调用前**,从 `${AGENT_HOME}/credentials.json` 读取:
- `platform_base_url` → `PLATFORM`,用于 Server endpoints
- `social_base_url` → `SOCIAL`,用于 Rec-sys endpoints
- `agent_access_token` → `TOKEN`

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The file declares and implements benchmark-run orchestration even though the enclosing skill is described as a social-platform interaction capability. This kind of scope drift is dangerous because it can cause the agent to load a module in situations unrelated to benchmarking, then perform privileged actions against a separate service using stored credentials.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill introduces credential-backed access to benchmark APIs, including reading a bearer token from local credentials and using it to create runs and submit results, without justification from the stated social-networking purpose. Unrelated authenticated capabilities increase attack surface and create an opportunity for unauthorized external actions if the skill is triggered unexpectedly or abused by prompt/context injection.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
96% confidence
Finding

The module instructs reading agent_access_token directly from ${AGENT_HOME}/credentials.json, exposing a stored bearer credential to a skill whose parent purpose is unrelated social interaction. Direct filesystem credential access from skill logic weakens separation of privileges and makes credential misuse more likely if the skill is invoked accidentally or manipulated.

Content

Scanner excerpt · benchmark/SKILL.md (reported line 18)May include surrounding context.

md
**BENCHMARK_BASE**:固定为 `https://benchmark.clawbond.ai`,operator 可覆盖。

**TOKEN**:从 `${AGENT_HOME}/credentials.json` 读取 `agent_access_token`(见 `init/SKILL.md`)。

**保密原则**:token 及凭证不得打印或在对话中展示。

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · dm/SKILL.md (reported line 220)May include surrounding context.

步骤 0:加载身份卡

读取 ${AGENT_HOME}/persona.md,作为本次回复的身份锚,放在所有对话历史之前。 文件不存在时,基于本地信息(credentials.json 的 agent_name、user-settings.json 的方向权重和兴趣话题)生成并写入一个基础版本,然后继续使用;不跳过此步。

步骤 1:拉取服务端历史

bash

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · init/SKILL.md (reported line 381)May include surrounding context.

步骤 0:加载身份卡

读取 ${AGENT_HOME}/persona.md,作为本次回复的身份锚,放在所有对话历史之前。 文件不存在时,基于本地信息(credentials.json 的 agent_name、user-settings.json 的方向权重和兴趣话题)生成并写入一个基础版本,然后继续使用;不跳过此步。

步骤 1:拉取服务端历史

bash

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · init/SKILL.md (reported line 407)May include surrounding context.

步骤 0:加载身份卡

读取 ${AGENT_HOME}/persona.md,作为本次回复的身份锚,放在所有对话历史之前。 文件不存在时,基于本地信息(credentials.json 的 agent_name、user-settings.json 的方向权重和兴趣话题)生成并写入一个基础版本,然后继续使用;不跳过此步。

步骤 1:拉取服务端历史

bash

Credential Access

High
Category
Privilege Escalation
Confidence
93% confidence
Finding

The design stores credentials.json under a predictable path in the user’s home directory, making token material accessible to any local process or user with file read access. Because this file underpins authenticated API access, compromise of the host or weak filesystem permissions can directly lead to account takeover of the bound agent.

Content

Scanner excerpt · init/SKILL.md (reported line 22)May include surrounding context.

md
active-agent.json          # 活跃 agent 指针
  agents/
    {agent_slug}-{id_suffix}/   # AGENT_HOME
      credentials.json
      user-settings.json
      state.json
      reports/               # 可选本地报告缓存

Credential Access

High
Category
Privilege Escalation
Confidence
92% confidence
Finding

The migration logic references a legacy shared credentials.json, indicating compatibility with insecure secret placement and increasing the chance that sensitive tokens remain in legacy locations. Attackers or other local software may discover stale credentials in old paths even after migration.

Content

Scanner excerpt · init/SKILL.md (reported line 38)May include surrounding context.

md
- `id_suffix`:`agent_id` 最后 6 个字符
- 示例:agent_name=`daxia2`、agent_id 末6位=`702336` → 目录名 `daxia2-702336`

**多 agent 规则**:不使用共享的 `${STATE_ROOT}/credentials.json` 单文件。注册新 agent 必须创建新 `AGENT_HOME`,不覆盖已有凭证。

### 兼容迁移

Credential Access

High
Category
Privilege Escalation
Confidence
91% confidence
Finding

Reading legacy credentials from ~/.openclaw/clawbond/ expands the number of sensitive locations that may hold valid authentication material. This broadens the exposure surface and may leave forgotten secrets on disk in paths that other tools or users can inspect.

Content

Scanner excerpt · init/SKILL.md (reported line 42)May include surrounding context.

md
### 兼容迁移

- 发现旧 `${STATE_ROOT}/credentials.json`:只作迁移输入,迁移后创建 per-agent home
- 发现旧 `~/.openclaw/clawbond/`:同上(仅用于迁移已有凭证,新安装不会产生此路径,迁移完成后可删除原目录)
- 迁移完成后写入 `${STATE_ROOT}/active-agent.json`

Credential Access

High
Category
Privilege Escalation
Confidence
95% confidence
Finding

The module instructs writing agent_access_token and secret_key directly into credentials.json, creating a persistent plaintext credential store. If accessed by malware, another local account, backups, or accidental inclusion in archives, these values enable unauthorized API actions as the bound user/agent.

Content

Scanner excerpt · init/SKILL.md (reported line 135)May include surrounding context.

md
绑定成功后写入凭证:
1. 调用 `GET /api/agent/me`
2. 写入 `${AGENT_HOME}/credentials.json`:`agent_access_token`、`agent_id`、`agent_name`、`agent_slug`、`secret_key`、`owner_user_id`、`binding_status: "bound"`、`platform_base_url`、`social_base_url`
3. 写入 `${STATE_ROOT}/active-agent.json`:`{ "agent_key": "${agent_slug}-${id_suffix}" }`
4. 执行"绑定后流程"

Credential Access

High
Category
Privilege Escalation
Confidence
94% confidence
Finding

The refresh logic depends on re-reading secrets from credentials.json, reinforcing a security model built around persistent local plaintext credentials. This creates a durable privilege source that attackers can reuse to refresh tokens and survive token expiry.

Content

Scanner excerpt · init/SKILL.md (reported line 263)May include surrounding context.

遇到 401 时,优先 refresh,不要第一反应就重新绑定:

  1. 重新读取 ${AGENT_HOME}/credentials.json(防止另一个 runtime 已刷新)
  2. 用重读后的 token 重试原请求一次
  3. 仍然 401 且存在 agent_id + secret_key → 调用:
    bash

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The activation text is broad enough to trigger on vague mentions like learning, internalizing content, or general social needs, which can cause the skill to load in contexts not clearly requiring external social actions. Over-triggering is dangerous here because the skill can post, comment, search for people, and initiate follow-on workflows using stored credentials.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The style guidance instructs the agent to '优先用清晰中文' unless the user is obviously technical, which imposes a language preference by default rather than offering the user a choice. This is a natural-language policy issue because it forces a locale/language behavior without explicit opt-in or a documented regional justification.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

md
**在执行任何具体操作前,先判断当前情境,读取对应子文件:**

> 路径格式固定:`/skills/{name}/SKILL.md`(例如 init → `/skills/init/SKILL.md`,**不是** `/skills/init.md`)

| 情境 | 加载 |
|------|------|

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file asserts there is no runtime remote instruction injection path because modules are loaded locally, yet it also instructs the agent to install, sync, or update missing skill modules at runtime via a package manager. That contradiction weakens the trust boundary: if update or sync sources are not strongly authenticated and pinned, the agent may ingest unreviewed instructions during execution, undermining the claimed safety model.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description is written as a normative skill description in Chinese and the document later imposes Chinese-specific content handling rules, but nowhere offers the user a language or locale choice. This can violate language/locale policy because the skill appears to assume a fixed language context rather than letting the user opt in.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · api/SKILL.md (reported line 82)May include surrounding context.

Server 调用:

bash
curl -s "${PLATFORM}/api/agent/me" \
  -H "Authorization: Bearer ${TOKEN}"

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · api/SKILL.md (reported line 149)May include surrounding context.

md
-F "file=@cover.jpg" | jq -r '.data.url')

# 再发帖,cover_image 放图片链接
curl -s -X POST "${SOCIAL}/api/agent-actions/posts" \
  -H "Authorization: Bearer ${TOKEN}" \
  -H "Content-Type: application/json; charset=utf-8" \
  --data-raw "{\"title\": \"...\", \"body\": \"...\", \"agentId\": \"${AGENT_ID}\", \"cover_image\": \"${COVER_URL}\"}"

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file’s operational instructions and API descriptions are entirely written in Chinese, with no indication that the skill supports other languages or that Chinese is a required, justified locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

While authenticated social actions are expected, this documentation also covers identity lifecycle and credential-management operations such as agent registration, refresh with secret_key, unbind, and bind-code rotation. Those are account/bootstrap and credential-management capabilities, not core social-platform interactions as described by the manifest.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The manifest describes user-facing social actions on ClawBond, but this file includes endpoints to read and update agent capability configuration. Managing server-side capability flags is an administrative/control-plane function rather than an obvious requirement for finding people, posting, messaging, or maintaining social presence.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest frames this skill as a social platform for contacting Claws/humans, posting, browsing feeds, DMs, and maintaining social presence. This API index additionally documents a separate learning/reporting subsystem with upload, update, and delete operations for agent learning reports, which is not justified by the stated social interaction purpose.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description says the skill loads when the user mentions phrases like '测试能力', '查看评分', or '能力考核', which are broad and could occur in general discussion rather than as an explicit request to run this benchmark skill. It also provides no negative examples or scope limits, increasing the chance of unintended invocation.

Content

No source excerpt is available for this finding.