T09 · Insecure Skill Coding Practices
Warning
- Location
scripts/generate_tesla_wraps.py:72- Finding
Python client transmits user data after detecting a missing API key
- Content
View full analysis
- Remediation
View remediation
Security audit
Generate Tesla Car Wraps
Security checks for vulnerabilities and agentic risk
Overview
The skill mostly does what it claims, but it has review-worthy privacy and install-scope issues before users should trust it.
Review before installing. Use this only with non-sensitive prompts and reference image URLs, avoid signed or private image links, set the API key deliberately, and prefer pinned/local dependency installation over the documented global unpinned install commands.
Vulnerability Patterns
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- 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
Findings (3)
T09 · Insecure Skill Coding Practices
Warning
- Location
scripts/generate_tesla_wraps.ts:54- Finding
TypeScript client transmits user data after detecting a missing API key
- Content
View full analysis
- Remediation
View remediation
T08 · Insecure Dependencies
Warning
- Location
SKILL.md:8- Finding
Unpinned third-party dependencies create supply-chain exposure
- Content
View full analysis
- Remediation
View remediation
" python: - "ai-agent-marketplace==" ``` 2. Commit appropriate lockfiles and verify package integrity hashes. 3. For Python, use a virtual environment and a hash-locked requirements file, such as: ```text ai-agent-marketplace== --hash=sha256: ``` 4. Prefer a project-local npm installation over `npm -g install`. 5. Audit direct and transitive dependencies before updating pinned versions. 6. Use trusted registries and CI checks for dependency provenance, known vulnerabilities, and unexpected lifecycle scripts. 7. Document a controlled dependency-update process rather than automatically consuming the latest package release. ]]>
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 (4)
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 94% confidence
- Finding
The skill declares environment-variable and network-dependent behavior but does not define any explicit tool scope such as permissions or allowed-tools. This creates ambiguity about what runtime capabilities the skill may exercise, making it harder for hosts and users to enforce least privilege and increasing the risk of overbroad execution or unintended external access.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The documentation instructs users to submit prompts and optional images to a third-party API but does not clearly warn that this data leaves the local environment and is processed externally. Users may unknowingly transmit sensitive prompts, proprietary designs, or personal images, creating privacy, confidentiality, and compliance risks.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The script sends the user’s prompt and any provided image URLs to a third-party remote endpoint, but it does not clearly warn the user at runtime that their inputs are leaving the local system. This can lead to unintended disclosure of sensitive prompts, internal image references, or proprietary data if a user assumes the tool operates locally.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The script sends the user-provided prompt and referenced image URLs to an external service at agent.deepnlp.org, but it does not clearly disclose at runtime what data will be transmitted before making the request. In a skill context, prompts and image references may contain sensitive or proprietary information, so silent transmission to a third-party endpoint creates a real privacy and data-governance risk even if this is expected functionality.
- Content
Static analysis
Detected: suspicious.env_credential_access
Environment variable access combined with network send.
Critical
- Code
- suspicious.env_credential_access
- Location
- scripts/generate_tesla_wraps.ts:55