Ai Product Description Generator Free

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 6:51 AM UTC
• Version: 2.0.1

Overview

This skill is a straightforward product-description generator with disclosed local and optional online AI backends, though users should avoid sending confidential product details to HuggingFace.

Use the default Ollama backend for private or unreleased product information. Only use the HuggingFace backend when you are comfortable sending the product name and features to HuggingFace, and install dependencies in an isolated environment from trusted package sources.

A.I.G

Vulnerability Patterns

• Insecure Dependencies: Introduces malicious components through unsafe dependency sources
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (1)

T08 · Insecure Dependencies

Note

• Location: scripts/script.sh:41

Finding

Unpinned Third-Party Dependency Installation Guidance

Content

View full analysis

Remediation

View remediation

``` 2. Generate and enforce cryptographic hashes: ```bash python3 -m pip install --require-hashes -r requirements.txt ``` 3. Install dependencies in an isolated virtual environment rather than the system Python environment: ```bash python3 -m venv .venv . .venv/bin/activate python3 -m pip install --require-hashes -r requirements.txt ``` 4. Document the trusted package index and discourage installation through untrusted mirrors or custom index URLs. 5. Avoid recommending installation with administrator or root privileges. 6. Consider replacing `requests` with Python standard-library HTTP functionality, which would remove this external runtime dependency. 7. Update `SKILL.md` so its requirements accurately disclose any third-party dependencies. If the dependency remains, remove the “standard library only” claim. ]]>

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Undeclared Tool Scope

Medium

• Category: MCP Least Privilege
• Confidence: 91% confidence

Finding

The skill advertises use of environment variables and network-capable backends, but it does not declare an explicit tool scope such as allowed-tools or permissions. That creates an authorization gap: an agent or runtime may permit broader-than-intended access, including reading secrets like HF_TOKEN and making outbound requests without clear user-visible constraints.

Content

No source excerpt is available for this finding.

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 80% confidence

Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/script.sh (reported line 96)May include surrounding context.

sh

model = os.environ.get("OLLAMA_MODEL", "llama3")
    payload = {"model": model, "prompt": prompt, "stream": False}
    print(f"[Ollama] Using model: {model} at {url.replace('/api/generate', '')}")
    resp = requests.post(url, json=payload, timeout=120)
    resp.raise_for_status()
    data = resp.json()
    return data.get("response", "")

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 84% confidence

Finding

This request sends user-supplied product data and features to the HuggingFace Inference API over the network. That is expected for the online backend, but it is still a real data-exposure risk if users provide confidential product information, internal launch details, or proprietary marketing content, especially because the transfer is to a third-party external service.

Content

Scanner excerpt · scripts/script.sh (reported line 113)May include surrounding context.

sh

"parameters": {"max_new_tokens": 400, "temperature": 0.7, "return_full_text": False},
    }
    print(f"[HuggingFace] Using model: {model_id}")
    resp = requests.post(api_url, headers=headers, json=payload, timeout=60)
    if resp.status_code == 503:
        print("Model is loading, please retry in ~30 seconds.", file=sys.stderr)
        sys.exit(1)

Static analysis

No suspicious patterns detected.