Security audit
RemoveMetadata
Security checks for vulnerabilities and agentic risk
Overview
This skill gives guidance and links for removing file metadata, with no bundled code or local file access, but users should consider the privacy implications of using the external website.
Install is reasonable for metadata-cleanup reminders. Before using the linked service with sensitive photos or documents, review the site's privacy terms and verify the cleaned file before sharing; metadata cleanup does not guarantee anonymity or remove visible content, watermarks, platform logs, or prior copies.
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.