Security audit
AgentProof
Security checks for vulnerabilities and agentic risk
Overview
This skill is a narrowly scoped guide for using AgentProof to authorize and verify repository patches, with explicit approval boundaries and no bundled executable payload.
Install only if you intend to use AgentProof for controlled repository changes. Verify the agentproof CLI provenance, protect receipt-signing private keys, and do not proceed past approval or execution steps unless the authority decision, trust fingerprint, repository scope, and receipt evidence are explicit and expected.
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