Security audit
booli-fpx
Security checks for vulnerabilities and agentic risk
Overview
The skill’s public property searches and explicitly approved browser connection fit its stated purpose.
Review the external CLI and extension before installing, since their releases were not fully audited here. Approve only booli.se with fetch capability and use a signed-out tab for these public queries. Pairing persists; revoke it through the extension popup when finished, following the [bridge’s revocation instructions](https://github.com/nullnet-app/contextmint-bridge/blob/main/docs/PRIVACY.md#6-revoking-access).
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