ClawHub
Back to skill

Security audit

DCL Secret Leak Detector

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed secret-scanning checklist with an optional paid MCP scan, and I did not find hidden execution, persistence, or credential-harvesting behavior.

Use the free checklist for highly sensitive material or when you do not want network transmission. Use the live MCP option only if you trust Fronesis Labs, accept the x402 payment flow, and are comfortable with the service receiving the text for scanning and recording hash/finding metadata on-chain.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 5)May include surrounding context.

md
name: dcl-secret-leak-detector
description: >
  Scan AI agent outputs, tool results, and pipeline data for exposed secrets
  and credentials — API keys, tokens, private keys, database URLs, .env values
  — before they reach users, logs, or downstream systems. Runs as a free
  instruction-only checklist, or as a real, paid regex scan via the live DCL
  Trust Oracle MCP server (Leibniz Layer™ protocol) with an on-chain audit

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 176)May include surrounding context.

md
**S1 — API Keys (Critical)**
- [ ] Short prefix followed by 20+ alphanumeric chars matching known provider key formats
- [ ] Live payment key prefixes (distinct from test/publishable key prefixes)
- [ ] Version control platform personal access token prefixes
- [ ] Messaging platform bot/user token prefixes

**S2 — Cloud Credentials (Critical)**