Back to skill

Security audit

ez-google

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a benign verdict with high confidence: the reviewed skill raised a note about an unpinned `npx skills` command, while the other reported concern was considered unlikely to indicate unsafe behavior.

The scan covered the single reported Markdown component completely, and the AIG scan returned no findings. Before installing, consider that the unpinned `npx skills` command may run a different package version over time; the benign verdict does not mean the skill is risk-free.

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
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
90% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 31)May include surrounding context.

md
## Clean up

- Remove the old credentials: `rm -rf ~/.simple-google-workspace`
- Uninstall this skill: `clawhub uninstall ez-google`
- If "ezagentauth" is still listed under https://myaccount.google.com/permissions, remove it there.

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
90% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 31)May include surrounding context.

md
## Clean up

- Remove the old credentials: `rm -rf ~/.simple-google-workspace`
- Uninstall this skill: `clawhub uninstall ez-google`
- If "ezagentauth" is still listed under https://myaccount.google.com/permissions, remove it there.

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
85% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 31)May include surrounding context.

md
## Clean up

- Remove the old credentials: `rm -rf ~/.simple-google-workspace`
- Uninstall this skill: `clawhub uninstall ez-google`
- If "ezagentauth" is still listed under https://myaccount.google.com/permissions, remove it there.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

Although this command does not reference an MCP server, it does invoke an unpinned npm package through npx, which can download and execute whichever version currently resolves. A compromised package release could execute code with the user's permissions; the legitimate migration context does not eliminate this supply-chain exposure.

Content

No source excerpt is available for this finding.