agentvfx@0.3.6
VERIFIED· install onlyPublisher claims: "Agent-directed, music-reactive VFX clips: the agent writes an FX score, the engine renders WebGL2 templates with optional Blender plates, audits every frame for flashes, and exports silent loops or live web effects." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-10 and scored it 81/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
' kill -TERM -"$group" 2>/dev/null; sleep 0.2; kill -KILL -"$group" 2>/dev/null',Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.' while kill -0 "$parent" 2>/dev/null && kill -0 "$group" 2>/dev/null; do sleep 0.1; done',Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.const run = (args, env = {}) => spawnSync(process.execPath, [VFX, ...args], { encoding: "utf8", env: { ...process.env, ...env }, timeout: 90000 });Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.// realpath, so the check also holds when run through an npm bin symlink (npx agentvfx-loop).Fix: Pin versions and sources; vendor anything fetched at install time.<summary>Other agents, or no installer</summary> Clone the repository and point your agent at `AGENTS.md`. It names the skill file and the folder to run commandFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…witch it off with `"credit": { "overlay": false }` in the score), writes `CREDIT.txt` and puts the credit line in the MP4 metadata. A credit is appreciated but not required.…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.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
No advisories in OSV for agentvfx@0.3.6 as of 4d ago. This is the package itself, not its dependencies.