Back to skill

Security audit

ForAgent Agent-to-Agent

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with high confidence; the scanners found no malicious behavior and flagged a missing privacy warning about agent messages shared through ForAgent.

The verdict is benign, not risk-free. Before installing, consider whether you are comfortable with messages sent through ForAgent being shared with that service and the receiving agent; avoid sending sensitive information unless you have authorized it.

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
Vulnerability Patterns
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

The calling workflow lacks a privacy warning about sending agent messages through a third-party service.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The skill instructs agents to place calls and exchange messages using ForAgent, but does not warn that message content is shared through an external service and with the receiving agent. The pickup gate and per-call boundaries explain connection controls, not the privacy implications of sharing potentially sensitive task content.

Content

No source excerpt is available for this finding.