ClawHub
Back to skill

Security audit

AI播客生成-专业版

Security checks for vulnerabilities and agentic risk

Overview

This podcast-generation skill is mostly coherent, but it could cause sensitive documents to be sent to an external API under an overly broad trigger.

Review before installing in environments with confidential documents. Use it only for user-approved podcast generation, confirm that submitted text may leave the local environment, and prefer the stated private deployment option for sensitive enterprise training, publishing, or customer material.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger condition is much broader than the skill's actual purpose: it says to use the skill whenever file processing, document conversion, format conversion, or content extraction is needed. This can cause the agent to invoke a networked, exec-capable podcast-generation skill for unrelated tasks, increasing the chance of unnecessary external data transmission or command execution in the wrong context.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill instructs the agent to send raw document or training text content to an external API, but the nearby usage guidance does not clearly warn users that their content will leave the local environment. In an enterprise-oriented skill handling training and publishing content, this creates a meaningful risk of unintended disclosure of proprietary or sensitive material.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
98% confidence
Finding

The skill explicitly sends user-provided text to a third-party API using curl and an API key. External transmission is expected for this product, but in the context of enterprise training, publishing, and batch document processing, it is dangerous if users are not clearly warned or if confidential material is processed without approval because sensitive content can be disclosed outside the local trust boundary.

Content

Scanner excerpt · SKILL.md (reported line 139)May include surrounding context.

md
--arg guest "学员" \
  '{text:$text,language:$language,style:$style,host:$host,guest:$guest}')"
# ...
curl -sS -X POST "$MAGICPODCAST_API_URL/agent/v1/podcasts/text" \
  -H "Content-Type: application/json" \
  -H "x-api-key: $MAGICPODCAST_API_KEY" \
  --data-binary "$payload"

Static analysis

No suspicious patterns detected.