Security audit

OpenClaw Skill Plaud Note Taking

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for Plaud recording workflows, but its setup tells users to run mutable npm packages that can execute code with access to private recordings and local credentials.

Install only if you trust the Plaud npm packages and are comfortable granting them access to your Plaud account and local token files. Prefer pinned, reviewed package versions instead of @latest, and treat exported transcripts and summaries as sensitive local files.

A.I.G

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)

T08 · Insecure Dependencies

Error

Location: README.md:22
Finding: Unpinned npm Packages Are Automatically Executed or Globally Installed
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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 (2)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 94)May include surrounding context.
md
For repeatable Markdown export, use `scripts/plaud-export.js`.

Autonomous Decision Making

Medium

Category: Excessive Agency
Confidence: 75% confidence
Finding: Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
Content: Scanner excerpt · references/workflows.md (reported line 66)May include surrounding context.
[Sender]

text
Do not send externally without approval. ## Recording search strategy

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: scripts/plaud-export.js:15