ClawHub
Back to skill

Security audit

bpm finder

Security checks for vulnerabilities and agentic risk

Overview

This BPM helper skill is coherent and disclosed; it runs a local Node script for tap/audio tempo analysis and does not show hidden persistence, exfiltration, or destructive behavior.

Install only if you are comfortable with the skill running a local Node script and ffmpeg against audio files you choose. Keep FFMPEG_PATH unset or pointed to a trusted ffmpeg binary, and do not provide sensitive local files unless you intend them to be analyzed locally.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (2)

Undeclared Tool Scope

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.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest frames this skill as BPM-finder help inside Codex, including tap tempo, conversion, normalization, and guidance, which suggests lightweight in-skill analysis. This script performs subprocess execution via ffmpeg discovery and decoding, including honoring an environment variable for the executable path, which is a materially broader capability than simple BPM assistance and is not explicitly justified by the manifest description.

Content

No source excerpt is available for this finding.

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
scripts/tap-tempo.js:576