Security audit
agent-card-signing-auditor
Security checks for vulnerabilities and agentic risk
Overview
This skill is a markdown-only auditor for Agent Card signing practices, with no bundled code, persistence, credential use, or hidden behavior found.
Installers should understand that this skill may cause the agent to fetch user-supplied Agent Card endpoints for audit purposes. Use it only with endpoints you intend to inspect, and do not provide private/internal URLs unless that is part of your own authorized review.
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
Static analysis
No suspicious patterns detected.