ClawHub
Back to skill

Security audit

Clause Explainer

Security checks for vulnerabilities and agentic risk

Overview

This is a plain-English contract clause explanation skill with no code execution, data access, persistence, or hidden behavior, though users should treat its legal guidance as informational only.

Use this for educational help understanding contract clauses, not as a substitute for a lawyer. Be careful with outputs based only on a clause type or excerpt, because jurisdiction, definitions, and other contract terms can materially change the answer.

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
  • 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 (2)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
90% confidence
Finding

The instruction to 'Never refuse for missing surrounding context' weakens safety boundaries by pushing the agent to provide authoritative-sounding legal interpretation even when critical context is absent. In a legal-analysis skill, this can cause overconfident or misleading outputs, especially for clauses whose meaning depends heavily on jurisdiction, defined terms, or interactions with other provisions.

Content

Scanner excerpt · SKILL.md (reported line 17)May include surrounding context.

md
## Working from a brief

Given the clause text (or a description), **explain it fully anyway**. If only a clause *type* is named, explain the typical version and note it should be checked against the actual wording. Never refuse for missing surrounding context; flag what the rest of the contract could change.

## Required Inputs

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The description says to use the skill when asked things like "what a clause means," "decode legal language," or "explain a term in a contract," but it does not define clear trigger boundaries or exclusion conditions. These phrases are broad enough to overlap with ordinary assistance requests about contracts, which could lead to unintended invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.