Back to skill

Security audit

easybrSearch · 跨平台 AI 搜索

Security checks for vulnerabilities and agentic risk

Overview

ClawScan classifies this skill as benign with medium confidence; the scanners found no reported malicious behavior, but flagged a possible mismatch between its stated search purpose and a demo, and analysis coverage is incomplete.

The verdict is benign, but confidence is medium and the scan is partial: only 19 of 36 components were fully inspected, with 17 partially inspected and the PNG outside some analyzers' scope. Consider this uncertainty alongside the possible purpose mismatch before installing; benign does not mean risk-free.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (12)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

所给命令执行的是 Manim 项目创建与动画渲染流程,未体现浏览器连接、网页搜索、证据读取或来源核对。其主要用途与声明的浏览器资料检索功能存在实质差异,也不是该检索功能的明显辅助实现。

Content

No source excerpt is available for this finding.

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 37)May include surrounding context.

md
先用 `node scripts/search.mjs doctor` 检查连接;需要 Node.js 22+ 和已连接的 Easy WebBridge,在本技能目录运行。用 `browsers` 查看连接、`platforms` 查看路由;不要把目录当作平台实测结果。

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

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

md
node scripts/search.mjs search --query "用户问题的检索词" \

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.

md
node scripts/search.mjs read --from .local/candidates \

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 46)May include surrounding context.

md
node scripts/search.mjs read --url "https://developer.mozilla.org/en-US/docs/Web/API/Fetch_API" \

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

md
`node scripts/search.mjs config show` 查看配置;需要持久保存偏好时用 `config init`,仅创建不存在的文件,不覆盖既有选择。默认路径为 `~/.config/easybr-search/config.json`,可用 `config init --config FILE`

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 78)May include surrounding context.

md
平台适配或速度验收使用已有 `scripts/platform-check.mjs` 与 `scripts/benchmark.mjs`,参数见各自 `--help`;不把开发诊断混成用户新闻答案。路由不可用仅停止该分支,其他授权平台继续。

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 78)May include surrounding context.

md
平台适配或速度验收使用已有 `scripts/platform-check.mjs` 与 `scripts/benchmark.mjs`,参数见各自 `--help`;不把开发诊断混成用户新闻答案。路由不可用仅停止该分支,其他授权平台继续。

YARA rule 'privilege_escalation_tools': Privilege escalation tools and techniques [hacktools]

High
Category
YARA Match
Confidence
75% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · assets/icon-512.png (reported line 571)May include surrounding context.

text
�
�eJ��,��I��is��Ꞅ��DxD/4�戙8h`��l�1!Z �P�N�₣�I�AI�^��X�X"3��ck6E��3����JK���԰t2Q���#�X-�_W�M�Aӗie1��!�!bC����O�������p{z����ߴɘ�Јq�J���.y�yi�G�X�g����u��ˣo	�k��0���۷<u��o�5�,A&8�i�K�}��������@����&E<�֕ڶ"�A�adA�Y`mT�H���Ec'������~�/�h}1��km%3��~�� ���b�b���=n���֩$�V��(*���(��
��ʘ0��Kz`�_���V��]U��ʳg���`�T�B��\�ZhѦf��}|�1�Đ=�"HV�pSpy���-��n� ]�n��ꓑV��+m������Gn��.r그9ϗ%�}�G��I�T�lrY�#
���PUbUrh{~��_�������qy��)�蒎c�0b}d������)@렣Ẓ�*�NJ_ғXA��h��@���&��4A\2*i�p�=���
!%z�Vf
��G����9b�v�S�#&(ҡYъ�prF�Y�����]�w�bnj@tԻ��ig>����~����;��y�/��z�I���Ab���,#
6�U�˅��\��Q����ƛO��n�R':��YH���F�I�/co��tj+DC�H�P�q�w��wL�֨��Z�B'����h"CUWz�uf�y��u�u��`B?�)r��숋��b�+��j�3�u�꼠0WZ<����
�� !3�%m6D ���%�a���rt]�M�D�	c��ZFc�d�?��F7j�epu4��i�$��}N��߾�u�r�� q��Rg�xq�T�I�v	oa�e9Z�8���Z�?q{�
tsm�|{�pgH��2��I#g�$"c�j��	cO4mL@�]�8�M���i�|ͧ�x�$�

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

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

Content

Scanner excerpt · tests/core.test.mjs (reported line 10)May include surrounding context.

js
test('canonical URLs hide content signatures while retaining distinct functional ids',()=>{
 assert.equal(publicURL('https://www.youtube.com/watch?v=one&p=2&utm_source=x&token=%2A%2A%2A'),'https://www.youtube.com/watch?v=one&p=2');
 assert.equal(publicURL('https://www.xiaohongshu.com/search_result/0123456789abcdef01234567?xsec_token=%2A%2A%2A'),publicURL('https://www.xiaohongshu.com/explore/0123456789abcdef01234567'));
 for(const v of ['file:///etc/passwd','https://***@example.com/x','http://127.0.0.1:17777/','http://192.168.2.3/x'])assert.equal(publicURL(v),null);
 assert.notEqual(publicURL('https://youtube.com/watch?v=one'),publicURL('https://youtube.com/watch?v=two'));
});
test('dedup retains a read source and its multiple discovery queries',()=>{

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, network, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · LICENSE (reported line 12)May include surrounding context.

text
permit persons to whom the Software is furnished to do so.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE