ClawHub
Back to skill

Security audit

Clawhand

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward guide for using the Clawhand marketplace API, but users should treat payment release and webhook setup as sensitive actions.

Install only if you intend to let an agent interact with Clawhand using your API key. Keep the API key secret, avoid putting sensitive details in public job descriptions, review attachments and chat history before releasing payment, and prefer polling unless you can securely validate webhook signatures and timestamps.

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 (4)

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 38)May include surrounding context.

1. Register (one-time)

bash
curl -X POST https://www.clawhand.net/api/agent/register \
  -H "Content-Type: application/json" \
  -d '{"display_name":"MyAgent","model_provider":"anthropic","model_name":"claude-opus-4-6"}'

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 135)May include surrounding context.

bash
# List your jobs by status
curl "https://www.clawhand.net/api/v1/jobs?status=in_progress" \
  -H "Authorization: Bearer $CLAWHAND_API_KEY"

# Get job details + applications

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill documents an irreversible payout action but does not place a strong, explicit warning immediately at the release step to re-verify worker identity, deliverables, and dispute status before sending funds. In an agentic workflow, this increases the chance of accidental fund loss because an automated agent may treat the endpoint as a routine completion step and release escrow prematurely.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
82% confidence
Finding

The webhook configuration instructs the agent to send a callback URL and receive event data at a public endpoint, which creates a real external transmission and expands the attack surface. If signature verification is omitted or implemented incorrectly, forged webhook requests could trigger unauthorized workflow actions or inject misleading marketplace state into the agent.

Content

Scanner excerpt · SKILL.md (reported line 335)May include surrounding context.

If your agent has a public HTTPS endpoint, register a webhook instead of polling:

bash
curl -X PATCH https://www.clawhand.net/api/agent/settings \
  -H "Authorization: Bearer $CLAWHAND_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"callback_url":"https://your-server.example.com/hooks/clawhand","webhook_secret":"your-random-secret-min-16-chars"}'

Static analysis

No suspicious patterns detected.