Security audit

plaud

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently connects a user's Plaud recordings to AgentPMT tools, but users should treat transcripts and setup commands as sensitive integration points.

Install only if you are comfortable letting AgentPMT access Plaud recording metadata, notes, and transcripts for the tasks you request. Prefer OpenClaw or pinned, reviewed setup paths over unpinned npx commands, and avoid sending confidential transcripts to downstream tools unless that sharing is intended.

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

Warning

Location: SKILL.md:144
Finding: Unpinned Third-Party Installer and Mutable Skill Dependencies
Content: View full analysis
Remediation: View remediation
add ... ``` 2. Pin `AgentPMT/agent-skills` to a specific reviewed commit hash or immutable release tag. 3. Publish and verify cryptographic checksums or signatures for downloaded skill content. 4. Vendor the required setup instructions into the audited package where practical, eliminating runtime retrieval of mutable instructions. 5. Use a lockfile and an approved internal package registry for installation tooling. 6. Run installation in a sandbox with restricted filesystem, credential, and network access. 7. Require explicit confirmation before executing externally retrieved setup content. 8. Re-audit dependency updates before changing the pinned package version or repository commit. ]]>

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (12)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill handles highly sensitive recordings, transcripts, and AI notes and explicitly describes flowing that content into AgentPMT-hosted services and other downstream tools, but it does not clearly warn users that their data may leave Plaud and be transmitted externally. In this context, the omission matters because meeting transcripts and voice memos often contain confidential business, personal, or regulated information, so users may unknowingly authorize broader disclosure than intended.
Content: No source excerpt is available for this finding.

Autonomous Decision Making

Medium

Category: Excessive Agency
Confidence: 80% 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 · SKILL.md (reported line 20)May include surrounding context.
md
Bring your Plaud recordings into every tool you already use. Plaud captures your meetings, calls, and voice memos as recordings, AI summaries, and full transcripts — and this makes all of it available to your AI assistant so nothing stays trapped in the app. Search recordings by name or date, pull speaker-attributed transcripts and AI notes, and build automations and workflows around what was said: follow-up emails, CRM notes, tasks, project updates, and shared documents. Connect Plaud once and every conversation you capture can flow automatically into the tools your team already runs on. ## Product Instructions Plaud captures the user's voice recordings along with AI-generated notes and full transcripts. The user must link their Plaud account once through the Plaud connection before any call succeeds — always use the stored account connection and never ask the user for a Plaud username or password. Typical flow: 1. Use list_files to find a recording. Filter with `query` (name substring) and/or `date_from`/`date_to` when the user references a specific meeting or day.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 70% confidence
Finding: npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 70% confidence
Finding: npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 70% confidence
Finding: npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 70% confidence
Finding: npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 70% confidence
Finding: npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 70% confidence
Finding: npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 70% confidence
Finding: npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
Content: No source excerpt is available for this finding.

External Transmission

Medium

Category: Data Exfiltration
Confidence: 50% confidence
Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Content: Scanner excerpt · SKILL.md (reported line 194)May include surrounding context.
md
- What AgentPMT is: ../what-is-agentpmt (ClawHub: `what-is-agentpmt`, page: https://clawhub.ai/agentpmt/what-is-agentpmt; skills.sh: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`) - AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup (ClawHub: `agentpmt-account-mcp-rest-api-setup`, page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup; skills.sh: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`) - Marketplace product: https://www.agentpmt.com/marketplace/plaud - AgentPMT main MCP server: https://api.agentpmt.com/mcp/ - AgentPMT REST invoke endpoint: https://api.agentpmt.com/products/purchase

External Transmission

Medium

Category: Data Exfiltration
Confidence: 50% confidence
Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Content: Scanner excerpt · SKILL.md (reported line 195)May include surrounding context.
md
- What AgentPMT is: ../what-is-agentpmt (ClawHub: `what-is-agentpmt`, page: https://clawhub.ai/agentpmt/what-is-agentpmt; skills.sh: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`) - AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup (ClawHub: `agentpmt-account-mcp-rest-api-setup`, page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup; skills.sh: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`) - Marketplace product: https://www.agentpmt.com/marketplace/plaud - AgentPMT main MCP server: https://api.agentpmt.com/mcp/ - AgentPMT REST invoke endpoint: https://api.agentpmt.com/products/purchase

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: This markdown file documents actions that retrieve AI-generated notes and full transcripts of recordings, which can contain sensitive personal or business information. The description presents these capabilities without any user-facing warning about privacy, confidentiality, or handling of recorded content.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.