T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:91- Finding
Plaintext HTTP Resource URLs with Unvalidated Query Parameters
- Content
View full analysis
- Remediation
View remediation
Security audit
Json To Jianying Description
Security checks for vulnerabilities and agentic risk
Overview
This is a narrow video-JSON conversion skill with no code execution or persistence, though it should only be used with trusted media JSON because it can expose raw media URLs.
Install only if you intend to process this specific Chinese-language video-material JSON format. Use trusted input, avoid publishing generated raw media links unless authorized, and prefer HTTPS plus proper URL encoding or server-generated signed links in any downstream implementation.
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/json-schema.md:55- Finding
Reference Schema Recommends Insecure Media URL Construction
- Content
View full analysis
- Remediation
View remediation
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 (3)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The skill explicitly extracts, constructs, and surfaces direct media URLs, including internal-looking download endpoints and resource identifiers, without any privacy warning or minimization guidance. This increases the risk of exposing sensitive asset locations, leaking internal infrastructure details, or redistributing private media links in generated output.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The trigger phrases are broad enough to match generic requests like '帮我生成一个视频' even when the user did not provide the expected structured JSON. That can cause incorrect skill invocation, unintended handling of unrelated user content, and accidental processing or disclosure of media/resource references outside the intended narrow format.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
This file's natural-language instructions and schema explanations are presented only in Chinese, which can amount to a language/locale policy violation when no user opt-in or justification is provided. The content does not indicate that the skill is region-specific or that alternative languages are available.
- Content