Security audit
Open Feed Recsys Reviewer
Security checks for vulnerabilities and agentic risk
Overview
This skill is a narrowly scoped review aid for public feed recommendation repositories and does not include hidden execution, persistence, or private-data collection behavior.
Before installing, expect this skill to help review public recommendation-system source code and claims. It should not be used as proof of live-platform behavior, reach prediction, or production equivalence unless the needed artifacts and user-supplied run evidence are available.
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
Static analysis
No suspicious patterns detected.