ClawHub
Back to skill

Security audit

sales-meeting-notes

Security checks for vulnerabilities and agentic risk

Overview

The skill uses limited local file access, but its script produces a checklist instead of the promised meeting notes.

Expect a field-checking report, not finished meeting notes. Review the actual content, owners, and dates yourself. Use a dedicated output folder because an existing meeting-record.md is overwritten. The optional unsigned Windows app is unnecessary for this workflow and falls outside this assessment.

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
  • 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)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The code's primary behavior is field-completeness and length checking, materially different from the declared note-to-record transformation. It expects the four fields to exist in the input already and omits their substantive values from meeting-record.md. A nonempty next_step passes regardless of whether it contains a date. Local file reads and writes are supporting implementation details; no unrelated access or external transmission is evident.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The skill produces a field-validation report rather than the promised structured meeting record.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

The manifest promises to turn raw sales call notes into decisions, commitments, open items, and a dated next step. At L093–L105, the code instead reads already-labeled fields and outputs only their character counts or EMPTY/TOO LONG statuses; L117 saves this report as meeting-record.md without including the actual meeting content. It neither extracts the promised information from raw notes nor produces a next step with a date.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.