Back to skill

Security audit

China Legal Analysis

Security checks for vulnerabilities and agentic risk

Overview

This is a small China-focused legal analysis skill with no executable code, permissions, credentials, network access, or persistence, though users should treat its legal guidance as informational only.

Before installing, understand that this skill is intended for Chinese-law scenarios and should not be relied on for other jurisdictions or important legal decisions without a qualified lawyer. Users should state the jurisdiction clearly when asking legal questions.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill description is broadly phrased to activate on general requests for legal analysis or guidance, which can cause overbroad routing of user queries into this specialized skill without clear boundaries. In a legal context, mistaken activation is riskier than in ordinary domains because users may receive jurisdiction-specific or quasi-legal guidance when they only wanted general information.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill is hard-scoped to Chinese law but the description does not require confirming the user's jurisdiction or obtaining explicit opt-in before applying that legal framework. This is dangerous because legal guidance is highly jurisdiction-dependent, and applying PRC legal assumptions to another country or region could materially mislead users about rights, obligations, deadlines, or remedies.

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