ClawHub
Back to skill

Security audit

thinking-map-territory

Security checks for vulnerabilities and agentic risk

Overview

This skill is a bounded reasoning aid that tells the agent to verify real code or data when assumptions conflict, without adding hidden execution or persistence behavior.

This appears safe to install as a reasoning workflow skill. Users should still apply normal care when a task's own verification step involves live systems or sensitive data, but the skill itself does not request broad authority or hidden access.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (1)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 51)May include surrounding context.

md
## Verification

- Falsify if you reasoned from the map without a territory observation, trusted a stale secondary source, or forced code to match a wrong doc without checking either.
- Stop when the contradiction is resolved or irrelevant to the decision.
- Over-application guard: do not re-verify the whole system when editing the map, when the map is the generative source of truth, or when the gap cannot change the next action.

Static analysis

No suspicious patterns detected.