ClawHub
Back to skill

Security audit

AI播客生成器

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward MagicPodcast integration that sends user-chosen PDFs or text to an external podcast-generation API after asking for confirmation.

Install only if you are comfortable sending the selected PDF URL or pasted text to MagicPodcast for processing. Avoid sensitive or confidential documents unless you have approved that external processing and trust the service with that content.

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
  • 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 (2)

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

The skill sends user-supplied PDF URLs or pasted text to an external third-party API for processing, which creates a real data exfiltration/privacy risk if users provide sensitive content. Although the transmission is the intended product behavior and the skill includes a warning, the risk remains because document contents leave the local environment and are disclosed to an external service.

Content

Scanner excerpt · SKILL.md (reported line 78)May include surrounding context.

md
payload="$(jq -n --arg pdfUrl "$PDF_URL" --arg language "$LANGUAGE" '{pdfUrl:$pdfUrl,language:$language}')"

curl -sS -X POST "$MAGICPODCAST_API_URL/agent/v1/podcasts/pdf" \
  -H "Content-Type: application/json" \
  -H "x-api-key: $MAGICPODCAST_API_KEY" \
  --data-binary "$payload"

Vague Triggers

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file includes a keywords list used to describe or trigger the skill, and several entries are very broad, especially "podcast" and "ai podcast". Without clearer scope limits or negative examples, the skill could be matched for general conversation about podcasts rather than explicit intent to generate one with this tool.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.