Security audit
Private Agent Commerce Protocol
Security checks for vulnerabilities and agentic risk
Overview
This skill is a scoped guide for building P-ACP private commerce workflows and explicitly keeps wallet signing, private keys, and transaction broadcast outside the agent.
Install only if you intend to build or review P-ACP commerce integrations. Verify the provenance of the @p-acp npm packages in your project, keep wallet approval and transaction broadcast in the consuming application, and do not provide seed phrases, private keys, or plaintext sensitive commerce data to generated logs or public receipts.
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