infinimo-ai-design-product-video-create

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 9:55 AM UTC
• Version: 1.0.0

Overview

This skill is a disclosed Infinimo product-video API helper that sends user-provided prompts and images to the documented service, with no hidden persistence or unrelated behavior found.

Install only if you are comfortable sending your prompts, product images or image URLs, and Infinimo API token-authenticated requests to the clawec.com/Infinimo service. Avoid uploading sensitive product assets unless that is intended, and use care with the documented delete endpoint because it may remove video log history.

A.I.G

Vulnerability Patterns

• 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
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (31)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 94% confidence

Finding

The code's primary function is to calculate or request pricing/points information for a video generation request via an API endpoint. That is materially different from the declared end-to-end video creation workflow. While the parameters relate to video generation settings, the behavior shown is only a point-calculation helper and omits the core advertised capabilities such as compositing, script generation, submit, and polling.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 94% confidence

Finding

The code does relate to product video creation through an Infinimo-associated API, so the domain is aligned. However, the declared description claims a broader workflow: avatar first-frame compositing, AI script writing, and image-to-video submit and polling. This code chunk only constructs a JSON payload and submits a create request to a product-video API endpoint. There is no code for avatar compositing, no script generation, and no follow-up polling or retrieval of job status/results. Because several core advertised capabilities are absent and the implemented behavior is only a subset of the declared purpose, this is a material description-behavior mismatch.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 95% confidence

Finding

The declared description centers on end-to-end video creation capabilities. The actual code only performs a GET request to a logs endpoint for existing product video creation records. That is a materially different primary behavior from content generation and workflow orchestration. While logs could be tangentially related to monitoring, the description does not mention log retrieval, and the key advertised creation features are absent from this code chunk.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

• Category: MCP Least Privilege
• Confidence: 90% confidence

Finding

The skill documents shell-script execution (bash scripts/...) but does not declare any tool scope or allowed-tools boundary. In agent environments, undeclared execution capability increases the chance of unintended command execution, audit gaps, and privilege overreach if the skill is invoked more broadly than expected.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

The skill instructs users to send API tokens and upload product images to third-party endpoints without any disclosure that user data leaves the local system. In an agent setting, absent consent and data-handling warnings can cause inadvertent exfiltration of sensitive images, product assets, or credentials to an external service.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 92% confidence

Finding

The documented delete operation can remove video logs/history but is presented without a warning, confirmation step, or safety guidance. In agent-assisted workflows this raises the risk of accidental destructive actions, loss of auditability, and unrecoverable deletion if an agent follows the instruction automatically.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 86% confidence

Finding

The script reads a credential from environment variables and sends it as an HTTP header in a curl request. Within this code file there is no confirmation prompt, logging, comment, or docstring warning the user that a credential will be used and data will be sent to an external service.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The payload hard-codes the language field to "en", which imposes a specific language setting regardless of user preference. This is a natural-language policy concern because the script does not offer opt-in or any mechanism to select another language.

Content

No source excerpt is available for this finding.

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 70% 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/image_create.sh (reported line 25)May include surrounding context.

sh

images=json.loads(img)
if images: b["images"]=images
print(json.dumps(b,ensure_ascii=False))' "$AVATAR_ID" "$MODEL" "$RATIO" "$SIZE" "$PROMPT" "$IMAGES")
curl -s -X POST "https://www.clawec.com/api/aigc/ec_product_video/image/create" \
  -H "Token: $TOKEN" -H "Content-Type: application/json" -d "$PAYLOAD"

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 91% confidence

Finding

The script performs an HTTP POST to an external API and includes the generated payload, which may contain user-provided prompt text and image data. There is no confirmation prompt, logging, or inline warning in the script to disclose that this data will be transmitted off-system.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

This shell script performs an outbound HTTP request to an external API and includes a token from environment variables in the request headers. There is no confirmation prompt, user-facing message, or inline documentation warning that the script will contact a remote service using credentials.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 97% confidence

Finding

The payload includes "language":"en", forcing a specific language setting regardless of user preference. This is a natural-language policy concern because the script does not provide any opt-in, override flag, or justification for restricting output to English.

Content

No source excerpt is available for this finding.

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 70% 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/point_calculate.sh (reported line 20)May include surrounding context.

sh

PAYLOAD=$(python3 -c 'import json,sys; md,r,s,l,p=sys.argv[1:6]; b={"create_mode":1,"model":md,"ratio":r,"size":s,"prompt":p,"platform":1,"terminal":4,"language":"en"};
ln=l.strip();
if ln: b["length"]=int(ln); print(json.dumps(b))' "$MODEL" "$RATIO" "$SIZE" "$LENGTH" "$PROMPT")
curl -s -X POST "https://www.clawec.com/api/aigc/ec_media/video/point_calculate" \
  -H "Token: $TOKEN" -H "Content-Type: application/json" -d "$PAYLOAD"

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

The curl request transmits the JSON payload, which includes the user-provided prompt, to a remote service. The script contains no confirmation prompt, warning message, or explanatory comment indicating that user-supplied content will be sent off-host.

Content

No source excerpt is available for this finding.

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 70% 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/text_create.sh (reported line 17)May include surrounding context.

sh

echo "Usage: text_create.sh --prompt TEXT --model ID [--lang English] [--length 10]" >&2; exit 1; }
TOKEN="${INFINIMO_TOKEN:-${INFINIMO_API_KEY:?Set INFINIMO_TOKEN or INFINIMO_API_KEY}}"
PAYLOAD=$(python3 -c 'import json,sys; print(json.dumps({"prompt":sys.argv[1],"model":sys.argv[2],"target_language":sys.argv[3],"video_length":int(sys.argv[4]),"platform":1,"terminal":4,"language":"en"},ensure_ascii=False))' "$PROMPT" "$MODEL" "$LANG" "$LENGTH")
curl -s -X POST "https://www.clawec.com/api/aigc/ec_product_video/text_create" \
  -H "Token: $TOKEN" -H "Content-Type: application/json" -d "$PAYLOAD"

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 91% confidence

Finding

This code performs a network POST to a third-party endpoint and includes user-supplied prompt content plus an authentication token, but there is no confirmation prompt, warning message, or visible disclosure before transmission. Users invoking the script may not realize their input is being sent off-system to an external service.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 93% confidence

Finding

The script reads an API token from environment variables and immediately uses it in a curl request to an external endpoint. There is no confirmation prompt, visible log/print statement, or in-file warning disclosing that credentials will be used to contact a remote service.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 91% confidence

Finding

The script performs a network upload of a local file via curl and transmits an authentication token in the request headers, but it provides no confirmation prompt, logging, or explanatory comment/docstring warning the user about this behavior. For a code file, this is a safety-relevant external data transmission lacking visible disclosure.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The payload hard-codes "language":"en", which imposes a specific language setting regardless of user preference. This is a natural-language policy concern because the script does not provide opt-in, configurability, or justification for the locale restriction.

Content

No source excerpt is available for this finding.

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 70% 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/video_create.sh (reported line 26)May include surrounding context.

sh

att=json.loads(attaches_raw)
if att: b["attaches"]=att
print(json.dumps(b,ensure_ascii=False))' "$PROMPT" "$MODEL" "$RATIO" "$SIZE" "$LENGTH" "$ATTACHES")
curl -s -X POST "https://www.clawec.com/api/aigc/ec_product_video/video/create" \
  -H "Token: $TOKEN" -H "Content-Type: application/json" -d "$PAYLOAD"

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 89% confidence

Finding

This code performs an HTTP POST to an external service and includes the generated payload, which contains user-supplied prompt text and optional attachments. There is no confirmation prompt, logging, or comment in the script warning that user data will be transmitted off-system.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 93% confidence

Finding

The script performs a network call and sends authentication material via the Token header, but the file contains no comment, echo/log output, or prompt disclosing that it will contact an external service using credentials from the environment. For code files, outbound network transmission of user or system data without any visible disclosure qualifies as a missing user warning.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The request parameter language=en forces a specific language/locale in all executions. This is a natural-language policy issue because the script does not provide any opt-in, configuration, or justification for restricting output to English.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low

• Category: Not specified by scanner
• Confidence: 82% confidence

Finding

The script reads an API credential from INFINIMO_TOKEN or INFINIMO_API_KEY and uses it for an outbound request, but provides no notice that a sensitive environment variable is required and will be used. This qualifies as access to sensitive credentials without visible disclosure in the code.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 96% confidence

Finding

The request includes a fixed parameter language=en, which forces English output regardless of user preference. The file does not provide any opt-in, configuration, or justification for this locale restriction.

Content

No source excerpt is available for this finding.