ClawHub
Back to skill

Security audit

PodcastIndex

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Podcast Index lookup helper that uses expected API credentials and outbound requests for its stated purpose.

Install only if you are comfortable providing Podcast Index API credentials and having podcast search terms sent to Podcast Index. Avoid using sensitive private terms in searches, and keep the API secret in environment/config storage rather than messages or logs.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

External Transmission

Medium
Category
Data Exfiltration
Content
Prerequisites
	•	Ensure PODCASTINDEX_API_KEY and PODCASTINDEX_API_SECRET are set in the environment or config.
	•	All requests must be authenticated with specific headers.
	•	Base URL: https://api.podcastindex.org/api/1.0
Authentication
To authenticate a request:
	1	Get the current Unix timestamp: unixTime = Math.floor(Date.now() / 1000)
Confidence
84% confidence
Finding
The skill is explicitly designed to contact an external service, so external transmission is expected in context; however, it still represents a real security/privacy concern because user queries and authenticated requests leave the local environment. The danger is increased by the presence of API credentials and the lack of clear user-facing disclosure or constraints on what may be sent.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill directs the agent to send user-supplied podcast queries plus authentication headers to a third-party API, but it does not disclose that user input and credential-derived authentication data are being transmitted externally. This creates a privacy and data-handling risk, especially if users assume searches are local or if sensitive search terms are sent without consent.

Static analysis

No suspicious patterns detected.