UGC Campaign Pipeline
Analysis
This appears to be a coherent UGC video-production workflow, with the main caveat that it chains other local media-generation tools and uses a provider API key.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
STEP 1: HERO IMAGE ... Tool: morpheus-fashion-design ... STEP 2: VARIATIONS ... Tool: multishot-ugc ... STEP 5: UGC VIDEOS ... Tool: veed-ugc (run 4 times) ... STEP 6: FINAL EDIT ... Tool: Remotion
The skill intentionally chains multiple generation and editing tools. This fits the stated pipeline purpose, but it means one user request can trigger several tool/provider operations.
uv run ~/.clawdbot/skills/morpheus-fashion-design/scripts/generate.py ... uv run ~/.clawdbot/skills/multishot-ugc/scripts/generate.py ... uv run ~/.clawdbot/skills/veed-ugc/scripts/generate.py
The skill does not include code itself but instructs use of scripts from other installed skills. Those dependencies are part of the effective trust boundary.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
COMFY_DEPLOY_API_KEY="..." uv run ~/.clawdbot/skills/morpheus-fashion-design/scripts/generate.py
The workflow uses a provider API key placeholder for generation commands. This is expected for external media generation, but the registry requirements list no required environment variables.
