ClawHub
Back to skill

Security audit

Abs Data Api

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a coherent ABS public-data lookup tool with disclosed API access and local caching, not a harmful or deceptive package.

Install if you are comfortable with the agent running local Python scripts, contacting the public ABS API, and storing public ABS metadata in a local cache. Treat Census/CED support as limited and prefer the dedicated census skill for Census DataPacks or complex Census workflows.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill documents and encourages executable capabilities including network access, reading/writing cache files, and likely environment access, but the skill metadata does not declare any permissions. That creates a trust and governance gap: a host may approve or route the skill assuming it is low-privilege while the bundled scripts perform live API calls and write under ~/.cache, which can lead to unintended data access or persistence.

Description-Behavior Mismatch

Medium
Confidence
88% confidence
Finding
The install note states the skill supports "Census / CED lookups when available in the ABS API," which conflicts with the skill metadata explicitly saying it is not for Census DataPacks and should use a different skill instead. This scope drift can cause the agent or operator to invoke the skill on unsupported data domains, producing incorrect results, policy bypass, or unintended access patterns under a misleading capability claim.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.