ClawHub
Back to skill

Security audit

Poyo Kling O3

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed PoYo Kling O3 API helper whose network submission behavior matches its video-generation purpose.

Install only if you intend to use PoYo for Kling O3 generation. Treat POYO_API_KEY as a secret, review payload JSON before submission, and avoid sending confidential prompts, private media URLs, or sensitive callback URLs unless you trust PoYo and the receiving webhook.

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
payload_file="$1"

curl --fail-with-body --request POST \
  --url "https://api.poyo.ai/api/generate/submit" \
  --header "Authorization: Bearer ${POYO_API_KEY}" \
  --header "Content-Type: application/json" \
Confidence
94% confidence
Finding
This script transmits the full contents of a user-supplied JSON file to an external third-party API using an Authorization bearer token. That behavior is intentional, but it is still a real data-exfiltration boundary: if sensitive, unreviewed, or attacker-controlled content is passed in, the skill will send it off-host without validation, redaction, or allowlisting.

External Transmission

Medium
Category
Data Exfiltration
Content
payload_file="$1"

curl --fail-with-body --request POST \
  --url "https://api.poyo.ai/api/generate/submit" \
  --header "Authorization: Bearer ${POYO_API_KEY}" \
  --header "Content-Type: application/json" \
  --data @"${payload_file}"
Confidence
91% confidence
Finding
The hardcoded remote endpoint shows that this skill is designed to send data to an external service on the public internet. In a security review context, this creates a genuine external transmission risk because all payload contents and associated metadata leave the local trust boundary, and there is no in-script control over what data is permissible to send.

Static analysis

No suspicious patterns detected.