Security audit
backlink-guard
Security checks for vulnerabilities and agentic risk
Overview
The skill’s backlink checks, optional paid services, and local records fit its purpose and include clear user approval controls.
The scanners reported no findings, and independent inspection resolved their two reference gaps. Before use, consider whether you trust the external PyPI package and optional API providers. Research queries go to external services, paid calls can exceed estimated limits, and results persist locally. Approve costs and review each proposed submission. This verdict covers the supplied instructions, not the unbundled CLI implementation.
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
