premiere-mcp-imt@1.3.1
CAUTION· install onlyPublisher claims: "Lets AI agents drive a running Adobe Premiere Pro (~440 verified operations). Works with every UI language Adobe ships and sees the frame: draws Object Masks on what it sees (a click for a person, a lasso for a face; ⊕/⊖, tracking) and places speed keyframes on the timeline by sight. A large skills library, built for Generative Extend, Generative Media, Object Mask, Enhance Speech." 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
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
NODE_AUTH_TOKENNPM_TOKENPREMIERE_UXP_TOKENTIMECODE_TOKENConfiguration, not credentials: AUDIO_KEYFRAME_READBACK, MCPB_SKIP_BUILD, npm_execpath, NPM_OTP, PASTE_ATTRIBUTES_MAX_KEYS_PER_PROPERTY, PR_MCP_FACADE, PREMIERE_DEFAULT_SEQUENCE_PRESET, PREMIERE_MCP_DEBUG, PREMIERE_MCP_PROTOCOL_MODE, PREMIERE_MCP_TITLE_DIR, PREMIERE_MCP_TRANSPORT, PREMIERE_TEMP_DIR, PREMIERE_TIMEOUT_MS, PREMIERE_UXP_PORT- Where it talks to
- no vendor host named in the codeAlso adobe.com, purl.org, iptc.org — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- use of the skill by an agent
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names adobe.com, purl.org, iptc.org as well as its own vendor. The guard injects NODE_AUTH_TOKEN, NPM_TOKEN, PREMIERE_UXP_TOKEN, TIMECODE_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
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 2026-11-13 and scored it 78/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Hidden zero-width characters detected; Privileged sudo command; Hidden zero-width characters detected. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
run(`npx -y @anthropic-ai/mcpb pack "${STAGING}" "${outFile}"`);Fix: Pin versions and sources; vendor anything fetched at install time.if (entry.name === "definition.json") output.push({ name: entry.name, data: Buffer.from("" + JSON.stringify(definition), "utf8") });Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.echo "Run: sudo \"$0\" --system" >&2Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.const definition = JSON.parse(definitionEntry.data.toString("utf8").replace(/^/, "")) as Record<string, any>;Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.+ "Install the signed MCPBridgeCEP.zxp from the GitHub release, or run `npx -y premiere-pro-mcp --install-cep`.",Fix: Pin versions and sources; vendor anything fetched at install time.run(`npx -y @anthropic-ai/mcpb validate "${join(STAGING, "manifest.json")}"`);Fix: Pin versions and sources; vendor anything fetched at install time.return /^?WEBVTT(?:[ \t]|\r?\n|$)/.test(content) ? "vtt" : "srt";Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.const lines = content.replace(/^/, "").replace(/\r\n?/g, "\n").split("\n");Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.if (entry.name === "definition.json") output.push({ name: entry.name, data: Buffer.from("" + JSON.stringify(definition), "utf8") });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
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim immersive-media-technologies: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- 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 type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.