Security audit
PRISMA 2020 review assistant
Security checks for vulnerabilities and agentic risk
Overview
This skill is a focused PRISMA 2020 review helper with only Markdown instructions and reference material, and I found no hidden execution, persistence, credential access, or unrelated behavior.
Before installing, consider that the skill may process manuscript drafts, reviewer comments, and related research material you provide. That behavior is expected for its purpose; avoid sharing confidential manuscripts unless your agent environment is appropriate for that content, and verify final compliance judgments against the official PRISMA guidance when needed.
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