ClawHub
Back to skill

Security audit

Quiver Quantitative

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Quiver Quantitative API helper that reads a disclosed API key and returns queried financial-data records as JSON.

Before installing, provide only a Quiver Quantitative API key you intend this skill to use, preferably scoped or revocable if Quiver supports that. Expect the skill to make authenticated Quiver API queries and print JSON results; there is no evidence in the artifact of persistence, local data indexing, or unrelated credential use.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill documentation indicates reliance on an environment variable (`QUIVER_API_KEY`) and execution of a local Python script, but it does not declare an explicit tool scope such as `permissions` or `allowed-tools`. In agent environments, this can cause the skill to run with broader-than-intended access to environment data, increasing the chance of secret exposure or unauthorized capability use if the script or surrounding workflow is modified or abused.

Static analysis

No suspicious patterns detected.