ClawHub
Back to skill

Security audit

Logic Hunter

Security checks for vulnerabilities and agentic risk

Overview

Logic Hunter is a straightforward fact-checking and evidence-scoring skill; its external search use is expected for that purpose, though users should avoid submitting sensitive claims to search tools.

Install only if you want research requests handled with evidence grading and red-team style critique. Treat searched claims as potentially shared with external search providers, and avoid using it for confidential, personal, or proprietary topics unless your environment's search tooling is approved for that data.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The README says users can trigger the skill by 'describing what you need' and gives examples like 'Analyze the credibility of [statement]'. These are common phrasings that could match everyday conversation, and the file does not define narrower trigger constraints or exclusion conditions for when the skill should not activate.

Session Persistence

Medium
Category
Rogue Agent
Content
Copy the skill files to your Claude Code skills directory:

```bash
# Create the skill directory
mkdir -p ~/.claude/skills/logic-hunter

# Copy the files
Confidence
60% confidence
Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Skill Enumeration

Medium
Category
Agent Snooping
Content
```bash
# Create the skill directory
mkdir -p ~/.claude/skills/logic-hunter

# Copy the files
cp SKILL.md ~/.claude/skills/logic-hunter/
Confidence
85% confidence
Finding
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill instructs the agent to call external search tools but does not warn that user queries may be transmitted to third-party services. This creates a privacy and data-governance risk, especially if users submit sensitive claims, internal topics, or proprietary research questions that are then sent off-platform without informed consent.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger conditions are broad enough to activate on ordinary research and verification requests, which can cause the skill to intercept general-purpose queries unexpectedly. In this skill, that matters because activation leads to external search and analysis steps, increasing the chance of unnecessary data disclosure and unintended tool use.

Natural-Language Policy Violations

Medium
Confidence
89% confidence
Finding
This code file contains natural-language strings and docstrings primarily in Chinese, including the module description and class description, while also exposing a CLI intended for direct user interaction. Under the policy, forcing a specific language without user opt-in is a locale/language policy violation unless the restriction is explicitly justified or optionality is offered.

Natural-Language Policy Violations

Low
Confidence
80% confidence
Finding
The description includes Chinese text ('证据溯源') embedded in otherwise English instructions, which introduces a language/locale inconsistency without explaining whether the skill targets bilingual users or offering language selection. Under the policy, language behavior should be opt-in or clearly justified when constrained.

Static analysis

No suspicious patterns detected.