T08 · Insecure Dependencies
Warning
- Location
SKILL.md:15- Finding
Unpinned Package Execution Through npx
- Content
View full analysis
- Remediation
View remediation
Security audit
Dental Self Care
Security checks for vulnerabilities and agentic risk
Overview
This dental self-care skill is mostly transparent about what it does, but it gives risky DIY dental guidance and stores sensitive personal health and financial details without enough safeguards.
Review this skill carefully before installing. Use it, at most, for reminders, supply lists, and finding low-cost dental providers; avoid relying on its DIY treatment or emergency instructions as a substitute for licensed dental or emergency care. Do not let it persist identifying health, income, location, or contact details unless you can control the file location, permissions, retention, and deletion.
Vulnerability Patterns
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- 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
Findings (3)
T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:88- Finding
Sensitive Health and Financial Data Stored in Unprotected Markdown Files
- Content
View full analysis
- Remediation
View remediation
other
Error
- Location
SKILL.md:63- Finding
Unsafe and Insufficiently Qualified DIY Dental Instructions
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- 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
Findings (4)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The description says to use the skill when the user lacks dental insurance, faces high costs, lives remotely, works irregular jobs, or simply needs to prevent emergencies. Those conditions are expansive and partially socioeconomic rather than clearly bounded to specific dental scenarios, increasing the chance of unintended invocation without explicit trigger constraints or exclusions.
- Content
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 94% confidence
- Finding
The skill instructs users to install and invoke
clawhubvianpxwithout pinning a specific version. That allows retrieval of whatever package version is current at execution time, creating a supply-chain risk where a compromised or malicious upstream release could execute arbitrary code in the agent environment.- Content
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 94% confidence
- Finding
This second unpinned
npx clawhubreference repeats the same supply-chain exposure in the user-facing command example. Because the skill content is meant to be copied and executed, an attacker who controls or compromises the published package/version could gain code execution on the host running the command.- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The phrase 'You simply want to minimize lifetime dental spending through prevention while maintaining peak oral function for daily living' is broad enough to match many generic wellness or frugality conversations. Because the file does not provide counterexamples or tighter activation boundaries, this can cause the skill to activate in everyday contexts where specialized dental guidance was not clearly requested.
- Content