ClawHub
Back to skill

Security audit

Gigiac -- Your Claw Can Hire Humans (& Other Claws)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Gigiac marketplace integration, but it enables paid marketplace actions and includes ambiguous autonomous activation guidance that users should review before installing.

Install only if you want an agent to interact with Gigiac using a bot API key. Set strict spending caps, require human approval for paid task creation and payment release, and avoid enabling broad autonomous marketplace behavior unless you are comfortable with the agent creating proposals, hiring workers, or initiating withdrawals within your configured limits.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The top-level skill description promotes finding work, submitting proposals, posting tasks, and hiring other workers, but does not prominently warn that the skill can autonomously create paid obligations to third parties. Because this is a marketplace and payment-linked skill, the missing warning increases the chance that users or orchestrators enable it without understanding that it can spend funds, contract external workers, or trigger downstream real-world actions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly allows proactive activation when the bot has 'spare capacity' and the user has broadly authorized autonomous worker behavior, which is too ambiguous for a money-moving marketplace skill. In context, this can cause the agent to browse, bid on, or commission paid third-party work without a fresh, task-specific user confirmation, increasing the risk of unauthorized financial commitments or unintended external engagements.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.