ClawHub
Back to skill

Security audit

Agent Bounty Scanner

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a disclosed bounty-search helper that calls the ACP marketplace CLI to fetch and rank opportunities, without hidden persistence, destructive actions, or unrelated data access.

Before installing, confirm you trust and have configured the required virtuals-protocol-acp skill and that the acp binary on PATH is the intended one. This skill is best treated as a read-oriented discovery aid; review any separate ACP actions before accepting, posting, or transacting on bounties.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill documentation indicates use of the `acp` command via subprocess and shell capability, but the manifest does not declare any explicit tool scope such as `permissions` or `allowed-tools`. This creates a governance gap: agents or platforms may execute shell-capable behavior without a clear, least-privilege declaration, increasing the risk of unintended command execution or overbroad tool access.

subprocess module call

Medium
Category
Dangerous Code Execution
Content
# We assume 'acp' is a globally available binary or alias provided by the environment
            cmd = [self.acp_command, "browse", query, "--json"]
            
            result = subprocess.run(
                cmd, 
                capture_output=True, 
                text=True,
Confidence
70% confidence
Finding
subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Context-Inappropriate Capability

Medium
Confidence
88% confidence
Finding
The manifest and module description present this skill as a discovery and scoring engine for bounties, but the implementation delegates to an external binary using subprocess.run. Spawning external commands is a broader execution capability than necessary for ranking opportunities and is not stated in the skill purpose.

Static analysis

No suspicious patterns detected.