Back to skill

Security audit

dep-check

Security checks for vulnerabilities and agentic risk

Overview

This dependency-checking skill is straightforward and disclosed, but users should confirm before letting it run package updates.

Install only if you want an agent to help with npm dependency checks. Treat update commands as project-changing actions: ask the agent to show proposed changes first, commit or back up work, review changelogs for major versions, and run tests after updates.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger dep is too short and ambiguous, making accidental activation highly likely in unrelated contexts. Because the skill includes commands and operational guidance, an unintended invocation could lead to confusing or unsafe recommendations in the wrong workflow.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger dep is too short and ambiguous, making accidental activation highly likely in unrelated contexts. Because the skill includes commands and operational guidance, an unintended invocation could lead to confusing or unsafe recommendations in the wrong workflow.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is scoped as checking for outdated npm dependencies, but it also instructs running npm audit and performing updates. This expands the skill from read-only inspection into security auditing and potentially state-changing package management, which can cause unintended actions, especially if an agent invokes follow-on update steps without explicit user confirmation.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
83% confidence
Finding

The trigger 过期 is very short and generic, and may refer to many non-technical concepts such as expired items or deadlines. In isolation it is prone to false matches, which can activate the skill in unrelated Chinese-language conversations.

Content

No source excerpt is available for this finding.