muapi-multi-angle-reshoot — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited muapi-multi-angle-reshoot (Agent Skill) and scored it 45/100 (orange). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 1 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
*.sig, SIGNATURES) outside the documentation.Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Re-render a subject or scene from multiple dramatic camera angles, such as fish-eye, bird's-eye, low-angle, and macro, while maintaining consistent identity and detail.
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
subject_description | text | yes | — | Description of the subject or scene (e.g. "a professional woman in a black suit holding a laptop"). |
reference_image | image_url | no | — | Optional reference image to maintain consistency across angles. |
If {{reference_image}} is not provided, submit the plan with ONE step to create the base subject:
muapi image generate (model=nano-banana-pro):A high-quality, professional photograph of {{subject_description}}. Clean studio lighting, sharp focus, realistic textures, cinematic quality.Present the base image to the user for approval.
Once the subject is established, submit the plan using muapi image edit (model=nano-banana-2-edit) to generate the requested angles. Use the approved image from Phase A as the reference for ALL steps.
A dramatic bird's eye view (from directly above) of the same subject. High-angle perspective, wide shot, looking down. Maintain exact clothing, face, and setting consistency.A high-distortion fish-eye lens photograph of the same subject. Ultra-wide angle, curved edges, dramatic perspective, immersive feel. Maintain exact clothing and face consistency.A low-angle "hero shot" looking up at the subject. Makes the subject appear powerful and dominant. Maintain exact clothing and face consistency.A stylized Dutch angle (tilted horizon) photograph of the same subject. Cinematic, slightly uneasy or dramatic vibe. Maintain exact clothing and face consistency.An extreme macro close-up focused on a specific detail of the subject (e.g., eyes, texture of the suit, or a feature of the laptop). Shallow depth of field, incredible detail. Maintain exact colors and textures.A worm's eye view from ground level looking straight up at the subject. Dramatic vertical perspective. Maintain exact clothing and face consistency.After generating the variations, present the multi-angle gallery to the user. You can also offer to generate specific individual angles based on their feedback.
multi angle, photo reshoot, change camera angle, fish eye view, birds eye view, low angle shot, macro photography, camera perspective
muapi CLI commands. Use muapi auth configure first if MUAPI_API_KEY is unset.curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}' and poll with muapi predict wait <request_id>.{{input_name}} placeholders with the user's actual inputs before issuing each call.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.