ClawHub
Back to skill

Security audit

Massat Security Audit

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple security-audit API wrapper, with the main risk being that audit targets are sent to a third-party service.

Install only if you are comfortable sending the audit target, such as a repository or system URL, to the BlindOracle/craigmbrown API. Do not submit private repositories, internal URLs, or regulated data unless you have approval and understand the provider's privacy, retention, and payment terms.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

External Transmission

Medium
Category
Data Exfiltration
Confidence
95% confidence
Finding

The skill instructs users or calling agents to POST a user-supplied target to an external third-party service, which creates a real data transmission risk. In a security-audit skill, this is especially sensitive because repositories, internal URLs, and related metadata may be confidential, and sending them off-platform can expose proprietary system details to an untrusted external endpoint.

Content

Scanner excerpt · SKILL.md (reported line 39)May include surrounding context.

bash
# Full audit (all 10 OWASP ASI categories)
curl -X POST https://craigmbrown.com/api/v1/massat/audit \
  -H "Content-Type: application/json" \
  -H "X-Payment: x402" \
  -d '{

Static analysis

No suspicious patterns detected.