T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:48- Finding
Media assets are retrieved over unencrypted HTTP
- Content
View full analysis
- Remediation
View remediation
Security audit
Jianying Video Compose
Security checks for vulnerabilities and agentic risk
Overview
This is a coherent video-composition skill, but it needs Review because it sends media to external UAT cloud services using unauthenticated APIs and plaintext asset URLs.
Use this only with approved, non-sensitive media unless the service owner confirms authorization, HTTPS-only asset delivery, access controls, retention/deletion rules, and quotas. Do not upload proprietary, personal, regulated, or confidential content to these UAT endpoints without explicit approval.
Vulnerability Patterns
- Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
- 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
Findings (2)
T09 · Insecure Skill Coding Practices
Warning
- Location
references/api_reference.md:3- Finding
Remote UAT media and rendering APIs are documented without authentication controls
- Content
View full analysis
- Remediation
View remediation
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 (4)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
This markdown file describes uploading user-provided media to OSS and calling remote API endpoints, but it does not warn users that local files and media content will be transmitted to external services. For markdown files, omission of warnings about behaviors affecting user data or privacy is in scope for missing user warnings.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 84% confidence
- Finding
The cloud rendering/export section explains remote video export and returns downloadable file URLs, but there is no disclosure that project content is processed by a cloud service. For markdown skill descriptions, privacy- or data-impacting behaviors should be explicitly warned about.
- Content
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The skill instructs users to upload files to a remote OSS endpoint but does not disclose data sensitivity, retention, access control, or transmission trust considerations. In an automation context, this can lead users to upload proprietary or personal media to a non-local service without informed consent, increasing risk of inadvertent data exposure.
- Content
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill describes cloud rendering/export and tells the user to wait for a returned video URL, but does not clearly warn that full project contents are sent to a remote rendering service. Because this skill handles end-to-end video composition, rendered projects may include sensitive source media, text overlays, and audio, so undisclosed remote processing creates a meaningful privacy and data-handling risk.
- Content
Static analysis
No suspicious patterns detected.