sogni-creative-agent-skill@3.68.1
CAUTION· static onlyPublisher claims: "CLI and agent skill for personal LoRAs, image, video, and music generation using Sogni AI's decentralized GPU network. Supports Pixal3D single- and multi-view image-to-GLB, BiRefNet background removal, Qwen3-TTS speech/voice cloning/design, MiniMax Music 3, SAM 3 object selection, promptless RTX VSR image upscaling through 16K, promptless FlashVSR and RelayVSR video upscaling up to 2160p, one-click image-folder loop reels, personas (people with saved photos and voices), persistent memories, custom personality, style transfer, angle synthesis, MiniMax H3/H3 Balanced/LightX2V Turbo/FastH3 Turbo (including audio-to-video from an uploaded track)/Seedance/HappyHorse/LTX/WAN video, music/lyrics, hosted chat, durable workflows, replay records, and multi-step creative workflows. Ask the agent to "draw", "generate", "create an image", "upscale an image", "upscale a video", "make a video/animate", "turn this image folder into a loop", "make music", "build a playable world", "apply a style", or "generate me as a superhero"." Observed in sandbox: static analysis only — behavior not yet observed.
Coverage
Static only; nothing was run yet.The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.
What changed since 3.68.0
vet-skills diff sogni-creative-agent-skill 3.68.0 3.68.1In the sandbox, this version reached for nothing 3.68.0 did not. Compared from the two recorded runs, not from source.
3.68.1 was not run in the sandbox (static only); the comparison covers what static analysis recorded only.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-16 and scored it 55/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Privileged sudo command; HTML comment carrying imperative instructions to the agent; HTML comment carrying imperative instructions to the agent. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.
Static findings
sogni-agent --json --video -m minimax-h3-fasth3-i2v-turbo --ref first.png --keyframe turn.png@3 --keyframe wave.png@6 --duration 8 --estimate-video-cost "<prompt>"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.: 'run `sudo sogni-agent self-update`';Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Generated by npm run sync:prompt-guides from @sogni-ai/sogni-intelligence-client 4.30.1; edit the rules there, not here.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.… this `SKILL.md` and invoke the `sogni-agent` CLI. The one-command alternative `npx setup-sogni-agent-skill --version=latest` auto-detects Claude Code, Codex CLI, and Hermes (it does not …Fix: Pin versions and sources; vendor anything fetched at install time.Generated by npm run sync:prompt-guides from @sogni-ai/sogni-intelligence-client 4.30.1; edit the rules there, not here.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.npm install -g @sogni-ai/sogni-creative-agent-skill@latestFix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.…rs on stdout. ## Uninstall Request Policy When a user asks to uninstall, run `npx setup-sogni-agent-skill --uninstall --remove-cli --purge`. This removes the skill files, the global CLI…Fix: Pin versions and sources; vendor anything fetched at install time.Generated by npm run sync:prompt-guides from @sogni-ai/sogni-intelligence-client 4.30.1; edit the rules there, not here.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.sogni-agent -m krea2_turbo_fp8_scaled -w 1024 -h 1024 -n 4 -o tile.png "<prompt>"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Generated by npm run sync:prompt-guides from @sogni-ai/sogni-intelligence-client 4.30.1; edit the rules there, not here.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.chmod 600 ~/.config/sogni/credentialsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.…(it does not configure Goose or OpenClaw). For Goose, install this skill with `npx skills add Sogni-AI/sogni-creative-agent-skill --global --agent goose --skill sogni-cr…Fix: Pin versions and sources; vendor anything fetched at install time.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
25 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim sogni-ai: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
- Unpinned dependencies≈ +1 on the totalPin exact versions (and ideally hashes) in package.json, requirements or the install script so the bundle cannot change under you.