T08 · Insecure Dependencies
Warning
- Location
skill.md:6- Finding
Unpinned Executable npm Dependency
- Content
View full analysis
- Remediation
View remediation
Security audit
Sales AI Agent Starter
Security checks for vulnerabilities and agentic risk
Overview
The skill mostly matches its stated business AI-agent purpose, but it installs an unpinned executable npm package that can change after review.
Install only if you trust the clawhub npm package source and are comfortable with an unpinned executable dependency. Use a sandbox or least-privileged environment, avoid production credentials during setup, and narrow any CRM, messaging, knowledge-base, or deployment access to the specific agent project.
Vulnerability Patterns
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- 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)
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
- 96% confidence
- Finding
The trigger phrases are very broad and include common requests such as "ai assistant," "create chatbot," and "build ai agent," which can cause this skill to activate for many generic user queries. This increases the chance of unintended routing, shadowing more appropriate skills, and exposing users to actions or advice outside the intended context of the skill.
- Content