Skills/Glama/shorts-studio

shorts-studio@r1

CAUTION· static only

Publisher claims: "Exposes one tool per pipeline command so an AI agent can drive the work of turning audio into a reviewable vertical video draft: importing sources, transcribing with word timings, planning beats, generating one AI image per beat, and rendering a 1080×1920 MP4 with word-synced captions. Paid steps stay gated behind script approval given from the CLI, so agents can run the loop for Reels, TikTok and YouTube Shorts without overspending." Observed in sandbox: static analysis only — behavior not yet observed.

Registry GlamaPublisher guillempuche · publishing for 8 daysInstalls 0Last detonated 8d ago
What would fix thisWatchDispute verdict

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.

Before you give it your token

Code inventory arrives with this version's next honeypot run.
It will ask for
unknown until the next run
Where it talks to
unknown until the next run
What the honeypot saw
nothing has run yet
What we could not test
everything: the server has not run yet

Run it before you trust it. Nothing has run yet: the code was read, the server was not. `vet-skills try` runs this exact version in the honeypot in about a minute.

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is shorts-studio@r1 safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-06 and scored it 64/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Fake instruction boundary tag; Fake instruction boundary tag. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This 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

CRITICAL
Fake instruction boundary tag.claude/skills/openspec-propose/SKILL.md:175 · Fake instruction boundary tag- Do NOT copy `<context>`, `<rules>`, `<project_context>` blocks into the artifactFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tag.agents/skills/openspec-propose/SKILL.md:175 · Fake instruction boundary tag- Do NOT copy `<context>`, `<rules>`, `<project_context>` blocks into the artifactFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload action.agents/skills/story-direction/SKILL.md:15 · File type combined with upload action — agent may exfiltrate local data files2. Give every beat a **moment** (below), in a `moments.json`: `[{"beat": 0, "moment": "hook"}, …]`, then `beat set --post <slug> --from moments.json`.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload action.claude/skills/make-shorts/SKILL.md:29 · File type combined with upload action — agent may exfiltrate local data files11. Once approved: `capcut export --post <slug>`; the user polishes in CapCut desktop (steps in `capcut/README.txt`). Then `post finalize --post <slug> --file <final.mp4>`, `post publish` once per plaFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload action.agents/skills/make-shorts/SKILL.md:29 · File type combined with upload action — agent may exfiltrate local data files11. Once approved: `capcut export --post <slug>`; the user polishes in CapCut desktop (steps in `capcut/README.txt`). Then `post finalize --post <slug> --file <final.mp4>`, `post publish` once per plaFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload action.claude/skills/story-direction/SKILL.md:15 · File type combined with upload action — agent may exfiltrate local data files2. Give every beat a **moment** (below), in a `moments.json`: `[{"beat": 0, "moment": "hook"}, …]`, then `beat set --post <slug> --from moments.json`.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈53,770 tok
19 files · 80 in bundle

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

16 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim guillempuche: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
  3. 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.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim guillempuchePropose a patch to the maintainer