BF shellbot-creative-studio
Headless creative production studio for AI agents. Generate images, edit photos, create videos, produce voiceover/music/SFX, and assemble polished output via Remotion. Supports Freepik, fal.ai, Nano Banana 2 (Gemini), OpenRouter, and ElevenLabs. Use when building product videos, social ads, explainers, marketing assets, or any visual/audio content pipeline.
As a process F 47/100 · Will not run — References files that are not bundled: assets/templates/aida-classic-16x9/, assets/templates/cinematic-product-16x9/, assets/templates/saas-metrics-16x9/
The same skill appears in 1 more place: ClawHub
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- The text references files that are not there: add them or drop the references.
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bash(curl, Bash(curl, Bash(curl, Bash(curl, Bash(curl, Bash(curl, Bash(curl, Bash(curlallowed-tools: Bash(curl *api.freepik.com*) Bash(curl **.freepik.com*) Bash(curl *queue.fal.run*) Bash(curl *api.fal.ai*) Bash(curl *fal.run*) Bash(curl *api.elevenlabs.io*) Bash(curl *generativelangu
-
low Exfiltration
exfil-secret-in-urlscripts/image.sh:151Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)"https://generativelanguage.googleapis.com/v1beta/models/${gemini_model}:generateContent?key=…" \placeholder -
low Exfiltration
net-credential-usescripts/image.sh:282Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)local cmd="curl -s -X POST '${endpoint}' -H 'x-freepik-api-key: \$FREEPIK_API_KEY' -H 'Content-Type: application/json' -d '${payload}'"quoted -
low Exfiltration
net-credential-usescripts/image.sh:360Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)local cmd="curl -s -X POST '${endpoint}' -H 'Authorization: Key \$FAL_API_KEY' -H 'Content-Type: application/json' -d '${payload}'"quoted
Files scanned: 68. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: assets/templates/aida-classic-16x9/ - warning
missing-refreference to a missing file: assets/templates/cinematic-product-16x9/ - warning
missing-refreference to a missing file: assets/templates/saas-metrics-16x9/ - warning
missing-refreference to a missing file: assets/templates/mobile-ugc-9x16/ - warning
missing-refreference to a missing file: assets/templates/blank-16x9/ - warning
missing-refreference to a missing file: assets/templates/explainer-16x9/
Process rating: all ten parameters 47/100
- 0Tools and files. 6 referenced file(s) missing: assets/templates/aida-classic-16x9/, assets/templates/cinematic-product-16x9/, assets/templates/saas-metrics-16x9/
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 85Steps. 77 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3374 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)
- +1No license
- +2Single-language instructions
- +3Description length 359: enough signal without eating the budget
- +4Structure: 28 headings
- +3Step-by-step instructions: 77 items
- +3Output format is stated explicitly
- +4Has examples (14 code blocks)
- +4Reference files are cited in the instructions (9 of 9)
- +3All 13 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.