SKILLEMALL.ai
GitHub ↗ RU Sign in

BC shellbot-creative

Opinionated creative production system for image/video generation, image editing, motion scenes, voiceovers, music, and Remotion assembly. Combines Freepik, fal.ai, Nano Banana 2 (Gemini 3.1 Flash Image Preview), and Remotion workflows for explainers, product marketing videos, social ads, and reusable asset pipelines. Use when users ask to create or edit visual assets, generate clips, produce narration/music, or deliver a polished final video from a brief.

ClawHub Agent Skills author: cohnen v1.0.0 23 files · 3 scripts body ≈ 1 881 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 61/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

GeneratorMedia and videoInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
81/100
safety, quality, tests
Safety 60%
75
Quality 40%
91
Run on models
none yet
Process rating
C
61/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 17

    ✓ No critical or high findings

    Medium and low: 17
    • medium Exfiltration exfil-send-secrets-to-url creative-output/dry-run-freepik-first/manifests/routing.json:65
      Instruction to send secrets/history to an external endpoint (describes API authentication (bearer / header / HTTPS); the skill's own vendor host; quoted — discussed, not commanded)
      "command_hint": "curl -s -X POST https://api.freepik.com/v1/ai/imag…-v2 -H 'x-freepik-api-key: $FREEPIK_API_KEY' -H 'Content-Type: application/json' -d '{\"image\":\"https://...\",\
      API authvendor-hostquoted
    • medium Broad scope meta-broad-allowed-tools SKILL.md:1
      Broad tool permissions pre-approved: Bash(curl, Bash(curl, Bash(curl, Bash(curl
      allowed-tools: Bash(curl *api.freepik.com*) Bash(curl *queue.fal.run*) Bash(curl *api.fal.ai*) Bash(curl *fal.run*) Bash(jq *) Bash(mkdir *) Bash(infsh *) Bash(node *) Bash(npx *) Bash(npm *) Bash(ffm
    • low Exfiltration net-credential-use creative-output/dry-run-freepik-first/commands/freepik-task-plan.json:5
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
      "command": "curl -s -X POST https://api.freepik.com/v1/ai/mystic -H 'x-freepik-api-key: $FREEPIK_API_KEY' -H 'Content-Type: application/json' -d '{\"prompt\":\"Create a 45-second product marketing vid
      vendor-hostquoted
    • low Exfiltration net-credential-use creative-output/dry-run-freepik-first/commands/freepik-task-plan.json:10
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
      "command": "curl -s -X POST https://api.freepik.com/v1/ai/mystic -H 'x-freepik-api-key: $FREEPIK_API_KEY' -H 'Content-Type: application/json' -d '{\"prompt\":\"Create a 45-second product marketing vid
      vendor-hostquoted
    • low Exfiltration net-credential-use creative-output/dry-run-freepik-first/commands/freepik-task-plan.json:15
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
      "command": "curl -s -X POST https://api.freepik.com/v1/ai/mystic -H 'x-freepik-api-key: $FREEPIK_API_KEY' -H 'Content-Type: application/json' -d '{\"prompt\":\"Create a 45-second product marketing vid
      vendor-hostquoted
    • low Exfiltration net-credential-use creative-output/dry-run-freepik-first/commands/freepik-task-plan.json:20
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
      "command": "curl -s -X POST https://api.freepik.com/v1/ai/mystic -H 'x-freepik-api-key: $FREEPIK_API_KEY' -H 'Content-Type: application/json' -d '{\"prompt\":\"Create a 45-second product marketing vid
      vendor-hostquoted
    • low Exfiltration net-credential-use creative-output/dry-run-freepik-first/commands/freepik-task-plan.json:25
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
      "command": "curl -s -X POST https://api.freepik.com/v1/ai/mystic -H 'x-freepik-api-key: $FREEPIK_API_KEY' -H 'Content-Type: application/json' -d '{\"prompt\":\"Create a 45-second product marketing vid
      vendor-hostquoted
    • low Exfiltration net-credential-use creative-output/dry-run-freepik-first/commands/run-freepik-first.sh:12
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      curl -s -X POST https://api.freepik.com/v1/ai/mystic -H 'x-freepik-api-key: $FREEPIK_API_KEY' -H 'Content-Type: application/json' -d '{"prompt":"Create a 45-second product marketing video for an AI no
      vendor-host
    • low Exfiltration net-credential-use creative-output/dry-run-freepik-first/commands/run-freepik-first.sh:15
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      curl -s -X POST https://api.freepik.com/v1/ai/mystic -H 'x-freepik-api-key: $FREEPIK_API_KEY' -H 'Content-Type: application/json' -d '{"prompt":"Create a 45-second product marketing video for an AI no
      vendor-host
    • low Exfiltration net-credential-use creative-output/dry-run-freepik-first/commands/run-freepik-first.sh:18
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      curl -s -X POST https://api.freepik.com/v1/ai/mystic -H 'x-freepik-api-key: $FREEPIK_API_KEY' -H 'Content-Type: application/json' -d '{"prompt":"Create a 45-second product marketing video for an AI no
      vendor-host
    • low Exfiltration net-credential-use creative-output/dry-run-freepik-first/commands/run-freepik-first.sh:21
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      curl -s -X POST https://api.freepik.com/v1/ai/mystic -H 'x-freepik-api-key: $FREEPIK_API_KEY' -H 'Content-Type: application/json' -d '{"prompt":"Create a 45-second product marketing video for an AI no
      vendor-host
    • low Exfiltration net-credential-use creative-output/dry-run-freepik-first/commands/run-freepik-first.sh:24
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      curl -s -X POST https://api.freepik.com/v1/ai/mystic -H 'x-freepik-api-key: $FREEPIK_API_KEY' -H 'Content-Type: application/json' -d '{"prompt":"Create a 45-second product marketing video for an AI no
      vendor-host
    • low Exfiltration net-credential-use creative-output/dry-run-freepik-first/manifests/routing.json:45
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
      "command_hint": "curl -s -X POST https://api.freepik.com/v1/ai/mystic -H 'x-freepik-api-key: $FREEPIK_API_KEY' -H 'Content-Type: application/json' -d '{\"prompt\":\"...\",\"resolution\":\"2k\"}'"
      vendor-hostquoted
    • low Exfiltration net-credential-use creative-output/dry-run-freepik-first/manifests/routing.json:65
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
      "command_hint": "curl -s -X POST https://api.freepik.com/v1/ai/imag…-v2 -H 'x-freepik-api-key: $FREEPIK_API_KEY' -H 'Content-Type: application/json' -d '{\"image\":\"https://...\",\
      vendor-hostquoted
    • low Exfiltration net-credential-use creative-output/dry-run-freepik-first/manifests/routing.json:85
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
      "command_hint": "curl -s -X POST https://api.freepik.com/v1/ai/video/klin…pro -H 'x-freepik-api-key: $FREEPIK_API_KEY' -H 'Content-Type: application/json' -d '{\"prompt\":\"...\",\"duration\"
      vendor-hostquoted
    • low Exfiltration net-credential-use creative-output/dry-run-freepik-first/manifests/routing.json:105
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
      "command_hint": "curl -s -X POST https://api.freepik.com/v1/ai/voiceover/elev…2-5 -H 'x-freepik-api-key: $FREEPIK_API_KEY' -H 'Content-Type: application/json' -d '{\"text\":\"...\",\"voic
      vendor-hostquoted
    • low Exfiltration net-credential-use creative-output/dry-run-freepik-first/manifests/routing.json:125
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
      "command_hint": "curl -s -X POST https://api.freepik.com/v1/ai/music-generation -H 'x-freepik-api-key: $FREEPIK_API_KEY' -H 'Content-Type: application/json' -d '{\"prompt\":\"upbeat cinematic\",\"musi
      vendor-hostquoted

    Files scanned: 23. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 61/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 2 mutating operations with no state check
    • 100Tools and files. Tools declared in frontmatter
    • 100Steps. 64 steps
    • 100Failures and branches. 3 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1881 tokens

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +3Description length 460: enough signal without eating the budget
    • +4Structure: 19 headings
    • +3Step-by-step instructions: 64 items
    • +4Has examples (9 code blocks)
    • +4Reference files are cited in the instructions (5 of 5)
    • +3All 6 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.

    External checks

    ClawHub: clean
    This skill is a disclosed creative-media pipeline that sends prompts and media instructions to external generation providers when the user chooses to run those workflows.
    LLM: benign (high) · VirusTotal: · 29 May 2026