Security audit
Yelp API
Security checks for vulnerabilities and agentic risk
Overview
This skill is a straightforward guide for using a paid Yelp-data API through fetcher.sh, with the payment and credential requirements disclosed.
Review fetcher.sh pricing and payment mechanics before use, especially the bearer-key and x402 options, because calls are paid and the skill says refunds are not provided on upstream failures. Install only if you are comfortable sending search queries and business/review requests to this third-party service.
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
