Back to skill

Security audit

Podcast And Audiograms

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed podcast repurposing guide that plans clips and audiograms without hidden execution, persistence, or credential handling.

Install this only if you want an agent to help plan podcast repurposing and you are comfortable providing episode materials, transcripts, retention analytics, and brand guidance. Review scheduled posts before publishing, and only use content you own or have permission to repurpose.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The eval uses a very broad trigger phrase, "Help me turn my podcast into social clips," which can match many adjacent media-editing or repurposing intents rather than uniquely invoking this skill. In a routing system, ambiguous invocation examples can cause the wrong skill to activate, leading to capability confusion, policy bypass through misrouting, or execution of a workflow with incorrect assumptions about available inputs and tool boundaries.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The phrase "Make me some podcast clips" is also overly generic and overlaps with other clipping or captioning skills, especially where multiple sibling skills handle short-form media transformation. In this skill family, broad phrasing increases the chance of incorrect routing, which is operationally risky because this skill has important scope limits around WoopSocial, clipping tools, hosting, and copyright boundaries.

Content

No source excerpt is available for this finding.