Back to skill

Security audit

getnote

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because its setup is reported to synchronize other Skills without clear separate authorization, and a generic phrase may trigger it unexpectedly.

Consider the review risks before installing. The findings indicate that ordinary wording may trigger the skill and that setup may change other Skills; the scan was partial because it could not resolve a local path-like reference, so the evidence is incomplete.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

L034 lists “记一下” (“note this”) as a trigger without requiring GetNote or knowledge-base context.

Medium
Category
Trigger Abuse
Confidence
88% confidence
Finding

“记一下” is common everyday speech that can mean remembering something within the current conversation rather than saving it to an external notes service. The skill does not exclude that interpretation or require an established GetNote destination, so this trigger can cause unintended invocation.

Content

No source excerpt is available for this finding.

The prescribed setup synchronizes other Skills despite an explicit promise not to modify other Skill files.

Medium
Category
Excessive Agency
Confidence
96% confidence
Finding

The mandatory connection workflow runs setup that synchronizes five domain Skills, despite the stated restriction against modifying other Skill files. This expands a connection request into persistent changes to agent instructions without separate authorization; the documented integration purpose reduces suspicion of malicious intent but does not eliminate the authorization gap.

Content

No source excerpt is available for this finding.

The connection workflow installs or updates domain Skills despite the manifest's promise not to do so autonomously.

Medium
Category
Excessive Agency
Confidence
95% confidence
Finding

The first-connection procedure bundles synchronization of five domain Skills into setup without requiring authorization for those persistent instruction changes. Although synchronization is openly documented and appears intended as integration maintenance, permission to connect an account does not necessarily authorize installation or replacement of agent Skills.

Content

No source excerpt is available for this finding.