Back to skill

Security audit

Video notes

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because scanners report capabilities beyond its stated video notes purpose, and part of its helper script could not be fully inspected.

Consider avoiding installation until the helper script has been fully inspected and the broader website and dependency features are clarified. The scan is incomplete, so it does not establish that the artifact is safe or that its author acted maliciously.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (4)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.

md
If MCP is unavailable, run the bundled helper `scripts/ink.mjs`:

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

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 implements general multi-source website extraction and refresh workflows beyond its declared video-transcript scope.

Medium
Category
Excessive Agency
Confidence
95% confidence
Finding

buildPack accepts up to five arbitrary public URLs, while refreshPack re-fetches their content and compares section changes. The CLI defaults pack extraction to full mode (L323), which the generated documentation explicitly describes as including up to 20 linked pages per source (L105); this is a general website-context workflow rather than extracting a public video's transcript for notes.

Content

No source excerpt is available for this finding.

The skill reads local dependency manifests and resolves package documentation through public registries, unrelated to video notes.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The dependencyDocs workflow reads user-specified local project manifests, extracts dependency names, and passes them to registry-resolution code that queries npm, PyPI, and crates.io (L256–L270). This exposes project dependency information to external registries and implements a software-documentation discovery capability with no connection to the stated video-transcript workflow; it is directly exposed through the deps command at L324.

Content

No source excerpt is available for this finding.