video-project-github@1.0.7
CAUTION· install onlyPublisher claims: "Keep an AI video project, or any agent-built project, in a private GitHub repo, even when the person has never used git. The agent does everything: creates the private repo, keeps keys out, saves a version after every approved step, stores big video and audio outside git so GitHub's 100 MB limit never hits, and restores the whole project byte for byte on a new laptop. Sets up the folder layout for mood boards, script, sound, characters, blockout, shots and the edit as text (HyperFrames, Remotion, ffmpeg), records the prompt, model, seed and cost of every take, and gives an undo for anything. Use for "put this on GitHub", "back up my video project", "don't lose my work", "undo", "go back to the old version", "move to a new computer", "organize my project folder", "file structure for an AI video", "edit video in the terminal", "git for video". Not for one-off clips with no later edits, or for teams already happy with their own git setup." 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 2026-11-13 and scored it 75/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
raise Stop("Move these keys to .env first, then run again:\n" + "\n".join(inline))Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.found.append(f"{rel}:{number} looks like a {label}. Move the value to .env (never saved) and read it from there.")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- Keys live only in `.env`, read from the environment. Never write a key in any other file or in a commit message.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- Keys live only in `.env`, read from the environment. Never write a key in any other file or in a commit message.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.line(bool(shutil.which("git")), "git", "winget install Git.Git" if win else "xcode-select --install" if mac else "sudo apt install git")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.hard-coded credentials, flagged or not. For each one add `NAME=value` to `.env`, put `$NAME` (or `process.env.NAME`) in the file, and runFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.SECRET_FILE = re.compile(r"(^|/)(\.env(\.[\w.-]+)?|.*\.pem|.*\.p12|.*\.key|id_rsa|id_ed25519|credentials(\.\w+)?|\.npmrc|\.netrc)$")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- Keys live only in `.env`, read from the environment. Never write a key in any other file or in a commit message.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.SECRET_OK_FILE = re.compile(r"(^|/)\.env\.(example|sample|template)$")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.7. Write AGENTS.md with these rules for every later session: save a version after each finished step; update media.lock.jsonl andFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Generated by .github/readme/build.ts from SKILL.md files and .github/readme/*.json. Edit those and run `bun .github/readme/build.ts`; CI fails when this file isFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.p = subprocess.run(cmd, cwd=cwd, text=True, capture_output=capture, input=input_text)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.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
5 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim vargai: 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.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.