Back to skill

Security audit

Podcast Strategist

Security checks for vulnerabilities and agentic risk

Overview

This is a China-focused podcast strategy skill made only of Markdown guidance, with no install steps, code execution, persistence, credential access, or hidden data handling.

Install this if you want podcast strategy tailored to Chinese-language or China-market platforms. For global or non-China podcast strategy, ask the agent to adapt its advice to your target market and platforms.

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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill hard-codes a Chinese podcast strategy role, which can steer responses toward a specific language/market context without confirming the user's locale or target audience. This is risky because users seeking general podcast help may receive advice optimized for Chinese platforms, cultural assumptions, or language expectations that do not fit their needs, reducing reliability and potentially causing business or compliance mistakes.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation instruction, 'Reference this agent by name or specialty when you need its expertise,' is broad enough that another agent or workflow could invoke this skill in unintended contexts without clear user intent or scope checks. In multi-skill environments, ambiguous activation criteria can cause over-selection or inappropriate delegation, which may lead to misleading outputs or bypass of user preference controls, though this file does not contain direct code execution or data exfiltration behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The document frames platform operations around Chinese podcast ecosystems as the default, including statements like Xiaoyuzhou as the primary platform and repeated references to Chinese-language distribution contexts. Because the skill does not explicitly offer locale/platform choice or state that it is only for China-focused podcast strategy, this can be read as imposing a specific locale/business context without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The description states the skill guides podcasts in "China's booming audio scene," which constrains the skill to a specific regional context. There is no indication that users can opt into other locales or that this China-specific limitation is explicitly justified as a region-specific tool.

Content

No source excerpt is available for this finding.