ClawHub
Back to skill

Security audit

China News

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently fetches Chinese news from public sources and creates a local report, with some disclosure and hardening improvements users should note.

Install this only if you are comfortable with the agent making outbound requests to public Chinese news/RSS sites and creating a dated Markdown news report in the workspace. For stricter environments, pin the Python dependency and ask the agent to confirm before saving or overwriting the report.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Note
Location
SKILL.md:7
Finding

Unpinned Third-Party Runtime Dependency

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (5)

Intent-Code Divergence

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The security notes say 'Local processing only', but the code performs multiple outbound HTTP requests to third-party RSS endpoints. This is a misleading security claim that can cause operators to trust the skill in restricted environments where external network access, request logging, or source contact is sensitive.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
80% confidence
Finding

The skill is designed to pull news specifically from Chinese sources, but generic descriptions and broad triggers can cause it to be selected even when the user did not opt into that geographic or editorial scope. This can lead to context mismatch, biased or irrelevant content retrieval, and unintended outbound requests to region-specific sources.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger phrases are broad enough to match ordinary requests like 'today's news' or 'what's trending', which can cause the skill to activate unexpectedly. In an agent ecosystem, overbroad invocation increases the chance of unanticipated network access and file creation when the user did not specifically request this skill or its Chinese-source behavior.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill writes a Markdown report into the local workspace without clearly disclosing that side effect in the manifest or user-facing behavior summary. Undisclosed file creation can surprise users, leave persistent artifacts, and in shared or automated environments may expose content retention or overwrite concerns even if the content is only news text.

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.txt (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 SOFTWARE OR THE USE OR OTHER

Static analysis

No suspicious patterns detected.