Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - Any file under `skills/` or any `SKILL.md` file (including its own)
Security audit
Defragmenter
Security checks for vulnerabilities and agentic risk
Overview
This skill reorganizes workspace knowledge into documented local files after user approval, with no hidden code, network behavior, or credential handling found.
Before installing, review proposed dry-run changes carefully because this skill can update persistent memory, flow, container state, and preference files that may shape future agent behavior. It should not be allowed to make silent edits or touch skill definitions, credentials, scripts, or files outside the workspace.
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
Findings (1)