ClawHub
Back to skill

Security audit

Podcast Show Notes Writer

Security checks for vulnerabilities and agentic risk

Overview

The bundled skill formats local podcast notes without hidden access or automatic publishing, but its output needs manual review.

Use a fresh output folder to avoid replacing an existing digest.md. Review the result against your original notes, especially sponsor disclosures and sections with unmatched headings. The script does not deliver all advertised writing features. The optional Windows app is unnecessary for this workflow and requires separate security review; a matching publisher-provided hash does not establish safety.

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 (2)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The script is a section-based formatter rather than the claimed raw-notes-to-publish-ready transformation. Content before the first heading or under unmatched headings is omitted, and missing material is replaced with placeholders rather than generated. Its local file reads and writes support the stated workflow; no unrelated resource access, network activity, or publishing behavior is present.

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.

Static analysis

No suspicious patterns detected.