Back to skill

Security audit

Anydef Enc

Security checks for vulnerabilities and agentic risk

Overview

This is a local encryption skill with no evident exfiltration, but its own implementation keeps extractable key material in memory without a clear lock mechanism.

Review this before installing if you expect strong protection against same-page script compromise. It appears local-only and purpose-aligned, but users should treat the vault as exposed while unlocked, understand there is no password reset, and prefer an implementation that uses non-extractable operational keys and clears in-memory key state on lock, logout, or session expiry.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/encryption-service.js:70
Finding

Extractable operational encryption keys remain exposed in page memory

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The function unlocks an existing vault using a passphrase and performs master-key rotation logic involving the KEK, which is sensitive credential-handling behavior. While there is a startup log message, it does not disclose the safety-sensitive nature of unlocking and re-wrapping encryption keys, and there is no confirmation prompt, warning comment, or user-facing notice about the impact of the operation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The natural-language navigation explicitly presents only English and Chinese sections, and the document does not state that these are optional examples or that users may choose other languages. Under the policy, forcing a specific language or locale without user opt-in can be a violation unless clearly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
98% confidence
Finding

The phrase 'after هر reboot' introduces a non-user-selected non-Latin script into operational instructions, which can confuse users, impair accessibility, and create ambiguity in security-critical recovery guidance. In a security/encryption skill, even small comprehension issues matter because users may misunderstand passphrase persistence or recovery expectations.

Content

No source excerpt is available for this finding.