ClawHub
Back to skill

Security audit

upgrade-deps

Security checks for vulnerabilities and agentic risk

Overview

This skill gives cautious instructions for dependency upgrades and does not show hidden, unrelated, or unsafe behavior.

Before installing, expect this skill to let the agent inspect manifests and lockfiles, run package manager and test/build commands, fetch release notes, edit dependency files, and create commits. Review the proposed upgrade scope when the dependency list is long, and pay attention to any forced resolution flags or uncovered runtime risks the skill reports.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description says to use this skill whenever the user says phrases like "update to the latest" or "fix the npm audit," even if they do not explicitly invoke the dependency skill. Those phrases can arise in broader troubleshooting or maintenance contexts, making the activation boundary ambiguous despite some exclusions being listed.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.