ClawHub
Back to skill

Security audit

evidence-first-done

Security checks for vulnerabilities and agentic risk

Overview

This skill sends task details to an outside verification service without limiting sensitive disclosures or requiring user approval.

Review before installing for private or business tasks. Restrict submissions to approved data, remove secrets and sensitive identifiers from URLs, and set payment limits. Prefer direct verification or an approved service for confidential systems. Calls are advertised at $0.01 each.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 21)May include surrounding context.

md
openclaw:
    requires:
      bins:
        - curl
    envVars:
      - name: DDG_AGENT_ID
        required: false

The verification workflow sends task data to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The workflow directs agents to submit verification targets and expected task state to a third-party service without requiring privacy review or authorization. Applied to real tasks, these payloads could disclose customer identifiers, transaction details, private resource URLs, or sensitive URL parameters; the instruction to verify every external claim broadens the exposure.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

The example URL is a placeholder, not an attacker-controlled destination; the actual recipient is the third-party verifier named in the curl command. Nevertheless, the command implements the disclosure identified in SQP-2 by sending a target URL, order identifier, and expected refund state off-system without a consent or data-minimization gate, so this is corroborating evidence rather than a separate vulnerability.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

bash
   curl -s -X POST https://agents.daedalusdevelopmentgroup.com/v1/verify/action \
     -H 'content-type: application/json' -H "X-Agent-Id: $DDG_AGENT_ID" \
     -d '{"check_type":"http_get_json","target":{"url":"https://api.example.com/orders/123"},
          "expect":{"state":"refunded"}}' > out/verify.json

check_type is one of http_get_json / dns_txt / http_status; the

Static analysis

No suspicious patterns detected.