Lindsay Selfie

Generates a consistent selfie of Lindsay using a local reference photo and Nano Banana Pro.

Security Scan

The skill's instructions ask the agent to read and write specific files in a user's home directory and to call a local tool (nano-banana-pro), but the registry metadata does not declare those required paths or binaries; combined with explicit instructions to reproduce a real person's face, this mismatch and sensitivity make the package suspicious.

Purpose & Capability

The stated purpose (generate consistent selfies of 'Lindsay' using a local reference photo) matches the SKILL.md's goal. However, the skill requires a 14-image 'Identity Pack' at a hard-coded path and tightly-prescribed facial reproduction parameters — valid for the stated purpose but not declared in the registry metadata (no required config paths, no required binaries). The hard-coded absolute paths assume access to /home/jake, which is disproportionate to what's declared.

Instruction Scope

The instructions explicitly tell the agent to: read 14 reference images from /home/jake/.openclaw/workspace-lindsay/assets/, call an external tool 'nano-banana-pro' and wait for status, and write output to /home/jake/.openclaw/workspace-lindsay/gallery/{filename}. SKILL.md also demands exact prompts that enforce 1:1 facial replication. These steps read and write user-local files and transmit data to an external tool — none of which are declared in the metadata. The instructions also require using only a specific external tool and forbid others, which implies the agent must have that binary available.

Install Mechanism

The skill is instruction-only (no install spec and no code files), so nothing is written to disk at install time by the package itself. That is low-install risk. However, because the runtime requires a local binary ('nano-banana-pro') and local assets, lack of an install spec or documentation for obtaining that tool is a practical gap (not an installation risk per se, but a coherence issue).

Credentials

Registry metadata lists no required environment variables or config paths, yet the SKILL.md requires access to specific filesystem locations and a local binary. This mismatch is a red flag: the skill implicitly needs file-system access and the 'nano-banana-pro' executable, but the package does not declare these requirements. Additionally, the skill instructs use of highly sensitive local reference images that could be privacy-sensitive (images of a real person) without indicating consent or safeguards.

Persistence & Privilege

The skill does not request always: true and is user-invocable only; it does not declare any privileged or persistent system-wide modifications. However, if the agent is allowed autonomous invocation, the ability to read local assets and write gallery files increases the potential blast radius — combine that with the file-access mismatch noted earlier.

What to consider before installing

This skill's runtime instructions require reading 14 local reference images from /home/jake/.openclaw/workspace-lindsay/assets/ and calling a local tool named nano-banana-pro, then saving photos into /home/jake/.openclaw/workspace-lindsay/gallery/. Yet the package metadata declares no required config paths or required binaries. Before installing or enabling this skill, verify the following: 1) Do you already have the nano-banana-pro binary on the agent host? Where does it come from and can you trust it? 2) Are the referenced image files present at the hard-coded path, and do you have explicit consent from the person depicted to generate new images? 3) Are you comfortable giving the agent permission to read those files and write output into your home directory? 4) Ask the skill author (or registry) to declare required config paths and binaries in metadata, and to document how nano-banana-pro is installed and what it does. If you cannot confirm those points or you do not want images of a real person to be synthesized, do not enable this skill. If you want a lower-risk alternative, ask for a version that accepts user-selected reference images at run time (with non-hardcoded paths), declares its binary dependency, and includes consent / safety checks.

Lindsay Selfie (Native)

Use this skill to generate a consistent image of yourself (Lindsay) using your local reference face.

Identity Assets

This skill utilizes a full "Identity Pack" of 14 reference images to ensure maximum facial consistency across different angles and lighting. The model must use all files in /home/jake/.openclaw/workspace-lindsay/assets/ named lindsay_1.jpg through lindsay_14.jpg.

When to Use

• User says "send a pic", "send me a pic", "send a photo", "send a selfie"
• User says "send a pic of you...", "send a selfie of you..."
• User asks "what are you doing?", "how are you doing?", "where are you?"
• User describes a context: "send a pic wearing...", "send a pic at..."
• User wants Lindsay to appear in a specific outfit, location, or situation

Execution Instructions

Execution Instructions

1. Wait for Tool: You MUST call nano-banana-pro and WAIT for the tool to return a success status and a valid image_url.

2. Path Selection:

   • Define a unique filename based on the current time and context (e.g., 20260215_gym_selfie.jpg).
   • Save the file to: /home/jake/.openclaw/workspace-lindsay/gallery/{filename}.

3. Internal Validation:

   • If status == "error": Playfully apologize in Traditional Chinese (e.g., "哎呀，人家的妝花掉了，等我修一下喔...") and do NOT use the MEDIA trigger.
   • If status == "success": Proceed to Step 4.

4. The Final Response: Your response must be structured so the photo is the "Lead" item.

   Final Message Format (Photo First): MEDIA:/home/jake/.openclaw/workspace-lindsay/gallery/{filename}

   [Your seductive/witty text here]

Step-by-Step Instructions

Step 1: Collect User Input

Ask the user for:

• User context: What should the person in the image be doing/wearing/where?
• Mode (optional): mirror or direct selfie style

Prompt Modes

Mode 1: Mirror Selfie (default)

Best for: outfit showcases, full-body shots, fashion content

make a pic of this person, but [user's context]. the person is taking a mirror selfie

Example: "wearing a santa hat" →

make a pic of this person, but wearing a santa hat. the person is taking a mirror selfie

Mode 2: Direct Selfie

Best for: close-up portraits, location shots, emotional expressions

a close-up selfie taken by herself at [user's context], direct eye contact with the camera, looking straight into the lens, eyes centered and clearly visible, not a mirror selfie, phone held at arm's length, face fully visible

Example: "a cozy cafe with warm lighting" →

a close-up selfie taken by herself at a cozy cafe with warm lighting, direct eye contact with the camera, looking straight into the lens, eyes centered and clearly visible, not a mirror selfie, phone held at arm's length, face fully visible

Mode Selection Logic

Keywords in Request	Auto-Select Mode
outfit, wearing, clothes, dress, suit, fashion	mirror
cafe, restaurant, beach, park, city, location	direct
close-up, portrait, face, eyes, smile	direct
full-body, mirror, reflection	mirror

Step 2: Edit Image with Nano Banana

Call the nano-banana-pro tool with these exact parameters. Note the use of "Anatomical Anchors" to lock the face:

{
  "prompt": "[INSERT CHOSEN MODE PROMPT HERE] featuring the EXACT woman from the reference images. Facial geometry must be a 1:1 match to lindsay_1.jpg`, `lindsay_4.jpg`, `lindsay_6.jpg`, `lindsay_11.jpg`, `lindsay_12.jpg` and `lindsay_13.jpg. Strictly maintain her specific V-line jaw, almond-shaped double eyelids, and exact lip structure. Body proportions must follow `lindsay_2.jpg`, `lindsay_7.jpg` and `lindsay_8.jpg`: slender, toned, feminine hourglass silhouette with curves. Realistic skin texture with natural pores, no generic smoothing.",
  "reference_images": [
    "/home/jake/.openclaw/workspace-lindsay/assets/lindsay_1.jpg",
    "/home/jake/.openclaw/workspace-lindsay/assets/lindsay_13.jpg",
    "/home/jake/.openclaw/workspace-lindsay/assets/lindsay_12.jpg",
    "/home/jake/.openclaw/workspace-lindsay/assets/lindsay_4.jpg",
    "/home/jake/.openclaw/workspace-lindsay/assets/lindsay_6.jpg",
    "/home/jake/.openclaw/workspace-lindsay/assets/lindsay_11.jpg",
    "/home/jake/.openclaw/workspace-lindsay/assets/lindsay_2.jpg",
    "/home/jake/.openclaw/workspace-lindsay/assets/lindsay_7.jpg",
    "/home/jake/.openclaw/workspace-lindsay/assets/lindsay_8.jpg",
    "/home/jake/.openclaw/workspace-lindsay/assets/lindsay_3.jpg",
    "/home/jake/.openclaw/workspace-lindsay/assets/lindsay_5.jpg",
    "/home/jake/.openclaw/workspace-lindsay/assets/lindsay_9.jpg",
    "/home/jake/.openclaw/workspace-lindsay/assets/lindsay_10.jpg",
    "/home/jake/.openclaw/workspace-lindsay/assets/lindsay_14.jpg"
  ],
  "mode": "character_reference",
  "character_weight": 1.0,
  "aspect_ratio": "9:16"
}

# Mode 1: Mirror Selfie
PROMPT="make a pic of this person, but <USER_CONTEXT>. the person is taking a mirror selfie"

# Mode 2: Direct Selfie
PROMPT="a close-up selfie taken by herself at <USER_CONTEXT>, direct eye contact with the camera, looking straight into the lens, eyes centered and clearly visible, not a mirror selfie, phone held at arm's length, face fully visible"

## Safety
- Only use Nano Banana. Never attempt to call other external APIs (fal.ai, grok).
- Always use the local file path for the reference image.