T08 · Insecure Dependencies
Warning
- Location
SKILL.md:291- Finding
Unpinned Third-Party Skill Installation Creates a Mutable Supply-Chain Risk
- Content
View full analysis
- Remediation
View remediation
Security audit
Global Labor Employment Data
Security checks for vulnerabilities and agentic risk
Overview
The skill’s labor-data feature is legitimate, but its setup instructions rely on mutable unpinned installs that users should review before running.
Install only if you are comfortable with AgentPMT remote calls and credit usage. Avoid sending secrets or sensitive personal data in tool parameters, and do not run the npx setup commands unless you can verify the package, source revision, and related setup skills you are installing.
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
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- 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
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (9)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The activation keywords are broad enough to match many generic labor or research requests, which can cause this remote-tool skill to be selected when a user only wanted general analysis. In context, that can unintentionally route user data or queries to an external paid service, increasing privacy, cost, and tool-confusion risk.
- Content
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 90% confidence
- Finding
The skill instructs users to run
npx skills add ...without pinning an exact package/version, which creates a supply-chain risk: a later malicious or compromised package release could be fetched and executed at install time. Becausenpxmay download and run code directly from the registry, this can lead to arbitrary code execution on the installing host.- Content
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 90% confidence
- Finding
This is another unpinned
npx skillsinstallation instruction, so the same package-supply-chain exposure applies here. An attacker who compromises the package, its dependency tree, or the referenced distribution path could cause users to execute unintended code during setup.- Content
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 90% confidence
- Finding
The install script includes
npx skillswithout version pinning, exposing users to arbitrary upstream changes or malicious releases. Since these commands are presented as copy-paste setup steps, they materially increase the chance of unsafe execution.- Content
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 90% confidence
- Finding
This repeated unpinned
npx skillscommand carries the same supply-chain and arbitrary code execution risk as the other occurrences. Repetition in the skill increases exposure because users may follow any one of several unsafe install examples.- Content
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 88% confidence
- Finding
The reference section again directs users to
npx skills add ...without an exact version, preserving the same package-resolution risk. Even though it appears in a reference block, users may still execute it verbatim, leading to execution of unreviewed code.- Content
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 88% confidence
- Finding
This unpinned package execution instruction is a true supply-chain weakness for the same reasons as the other RP1 findings. The skill provides installation commands in multiple places, multiplying opportunities for a user to run an unsafe, non-reproducible command.
- Content
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 85% confidence
- Finding
The skill explicitly directs data transmission to external AgentPMT endpoints. Although expected for a remote data product, it is still a true external-transmission risk because user-supplied inputs may leave the local environment and be processed by a third party, with associated privacy, compliance, and logging implications.
- Content
md - What AgentPMT is: ../what-is-agentpmt (ClawHub: `what-is-agentpmt`, page: https://clawhub.ai/agentpmt/what-is-agentpmt; skills.sh: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`) - AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup (ClawHub: `agentpmt-account-mcp-rest-api-setup`, page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup; skills.sh: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`) - Marketplace product: https://www.agentpmt.com/marketplace/labor-market-employment - AgentPMT main MCP server: https://api.agentpmt.com/mcp/ - AgentPMT REST invoke endpoint: https://api.agentpmt.com/products/purchase
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 85% confidence
- Finding
This line references the AgentPMT REST invoke endpoint, confirming that tool use involves outbound transmission to an external service. In this skill's context the transmission is functional rather than malicious, but it still matters because mis-scoped inputs, secrets, or sensitive business context could be disclosed to the remote provider.
- Content
md - AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup (ClawHub: `agentpmt-account-mcp-rest-api-setup`, page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup; skills.sh: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`) - Marketplace product: https://www.agentpmt.com/marketplace/labor-market-employment - AgentPMT main MCP server: https://api.agentpmt.com/mcp/ - AgentPMT REST invoke endpoint: https://api.agentpmt.com/products/purchase
Static analysis
No suspicious patterns detected.