Back to skill

Security audit

Memory Archiver

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed memory log archiver, but users should understand it can delete archived originals by default.

Before installing, confirm you want old memory logs summarized into MEMORY.md and originals deleted after archiving. Consider setting delete_after_archive to false or keeping backups if the memory files may contain information you need verbatim.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly documents automatic deletion of original memory files after archiving, but does not clearly warn users about the risk of irreversible data loss, archive corruption, or incomplete extraction before deletion. In a scheduled automation context, this can cause silent destruction of user data or long-term memory records if the archive step fails or produces unusable output.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill's natural-language instructions and operational descriptions are presented entirely in Chinese, which effectively forces a specific language for users without any opt-in or stated regional justification. The policy requires either offering a language or locale choice or clearly documenting why the constraint is necessary.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.