Back to skill

Security audit

Counter Evidence Hunter

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed research-assistant skill for finding counter-evidence, with no executable code, persistence, credential access, or hidden behavior found.

Install this if you want a Chinese-language workflow for challenging a main conclusion with counter-evidence. Be aware it may activate broadly around high-risk or uncertainty-heavy reasoning, so review its output as an adversarial evidence aid rather than a final decision.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description says to use the skill whenever there is a need to reduce hallucinations, supplement alternative narratives, or before high-risk decisions. These conditions are very broad and could match many ordinary reasoning tasks, without clear boundaries or negative examples showing when the skill should not activate.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The natural-language instructions and schema descriptions are written entirely in Chinese, which effectively imposes a language/locale expectation on use of the skill. There is no statement offering multilingual output or explaining that the skill is intentionally limited to Chinese-speaking users or a specific region.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown file is written entirely in Chinese and provides no indication that users may choose another language or that the locale restriction is required for a region-specific purpose. 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.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file presents all headings, scenario descriptions, and example content exclusively in Chinese. Under the policy rule, forcing a specific language without user opt-in or a documented region-specific justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This markdown file contains user-facing instructional content exclusively in Chinese, and there is no indication that the skill is limited to a Chinese-speaking audience or that language selection is optional. 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.

Static analysis

No suspicious patterns detected.