ClawHub
Back to skill

Security audit

contract-summary-explainer

Security checks for vulnerabilities and agentic risk

Overview

The skill keeps contract handling local and under user control, although its bundled script checks fields rather than producing the promised contract analysis.

Expect the agent to perform the substantive review; the script cannot establish that contract risks were checked. Verify summaries against the original clauses and obtain legal review for important decisions. Keep confidential documents within the authorized environment. The optional unsigned Windows app is unnecessary for this workflow and requires a separate trust decision.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The script's primary function is brief validation, not contract explanation or analysis. Its output contains field lengths, missing-field notices, and static guardrails, but not even the supplied summary content. Local input reading and report writing are ordinary supporting operations; the mismatch is the substantive gap between the declared contract-analysis capabilities and the implemented field-validation behavior.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The script produces a field-length validation report rather than the contract summary, clause mappings, and risk analysis promised by the manifest.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The implementation reads prepopulated summary fields and reports only whether they are missing or exceed character limits; it does not summarize contract text, map statements to clauses, or identify risky terms. Despite this, it writes the result as contract-summary.md, so the generated artifact does not provide the substantive review described by the skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.