Back to skill

Security audit

adc-patent-weekly-report

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow Markdown-only skill for generating ADC patent intelligence reports, with no executable code, persistence, or hidden data handling.

Reasonable to install if you need Chinese-language ADC patent intelligence reporting. Users should still verify source coverage and dates, and treat FTO, infringement, validity, and claim-comparison outputs as research support rather than legal advice.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Natural-language content in the description and usage examples appears to require Chinese, but the file does not state that the skill is region-specific or that users may choose another language. This can violate language or locale policy when a skill effectively forces a specific language without opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger phrases are generic product/technology analysis requests and do not clearly delimit when this skill should activate versus a broader research or patent-analysis workflow. In an agent environment, ambiguous activation boundaries can cause over-invocation, unintended handling of legal or competitive-intelligence tasks, and increase the chance that the skill is used outside its intended scope.

Content

No source excerpt is available for this finding.