Paper Writing Workflow
Analysis
This appears to be a benign paper-writing workflow, with only purpose-aligned local script use and reliance on separately installed companion writing/research skills.
Findings (2)
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.
"required": ["scientific-writing", "academic-writing", "research-paper-writer", "citation-management"]
The workflow delegates important stages to other skills that are not included in this artifact set. This is disclosed and purpose-aligned, but it extends trust to separately installed components.
python paper_writing_workflow.py --template scientific_data --topic "AI psychology research"
The skill instructs use of a local Python helper. The provided script is small, purpose-aligned, and shows no shell, network, credential, or dynamic-execution behavior, but users should still recognize it as local code execution.