T09 · Insecure Skill Coding Practices
Warning
- Location
scripts/doubao_media.py:25- Finding
Bearer API Key May Be Forwarded Across Trust Boundaries During Redirects
- Content
View full analysis
- Remediation
View remediation
Security audit
Doubao Image Video
Security checks for vulnerabilities and agentic risk
Overview
This is a coherent Doubao media-generation helper that calls Volcengine Ark with the user's API key and can optionally download videos, with clear cautions but no hidden or deceptive behavior found.
Install only if you are comfortable sending media prompts, image URLs, and task metadata to Volcengine Ark using your DOUBAO_API_KEY. Use --download-to with a new, non-sensitive filename because the helper may replace an existing file at that path, and avoid using the skill with private image URLs or sensitive prompts unless that third-party transfer is acceptable.
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
scripts/doubao_media.py:123- Finding
Unvalidated and Unbounded Download of API-Supplied Video URL
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- 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)
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 92% confidence
- Finding
The skill invokes a Python script that uses environment secrets and performs network operations, but the manifest does not declare an explicit tool scope such as permissions or allowed-tools. This weakens reviewability and enforcement because operators and users cannot easily see or constrain the capability surface before execution.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The skill sends user prompts and possibly image URLs to Volcengine Ark and can write downloaded output files locally, but the user-facing description does not clearly warn about third-party data transmission or local file creation. This creates privacy and safety risk because sensitive prompts, URLs, or generated content may be sent off-host or written to disk without informed consent.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The wait command will download arbitrary remote content to a caller-controlled path and opens that path with write-binary mode, which will silently overwrite an existing file if it already exists. In an agent or automation context, this can clobber important local files, and because the downloaded URL comes from an external API response, the feature also turns remote task output into a local file write primitive.
- Content
Static analysis
No suspicious patterns detected.