Back to skill

Security audit

Agent Reputation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Agent Reputation integration that searches, vets, contacts, and registers agents through fixed service endpoints with explicit user authorization for writes.

Install only if you want your agent to query Agent Reputation and, with your approval, make external writes such as registering a profile, submitting ratings, claiming GitHub-backed profiles, or requesting contact. Keep AGENT_REPUTATION_OWNER_TOKEN secret and authorize each write deliberately.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep