Paper DeepRead Comic Studio
PassAudited by ClawScan on May 4, 2026.
Overview
The skill appears coherent for paper deep-reading, storyboard generation, and local PDF assembly, with expected notes around optional local scripts and external image-generation services.
This skill looks safe to install for its stated purpose. Before using it, be aware that optional Python helpers may read local project files and write PDFs, and image-generation steps may send paper-derived prompts to an external provider. Use trusted project directories and avoid external image APIs for confidential papers unless approved.
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.
If the user runs the helper, it will access local image files in the chosen directory and create PDF output files.
The final PDF workflow can run a local Python helper that reads image files and writes a PDF. This is expected for the stated PDF assembly purpose, but it is still local code execution.
Use `scripts/assemble_storyboard_pdf.py` or an equivalent local implementation with PIL/Pillow or ReportLab.
Run the helper only in a trusted project folder, review input/output paths before execution, and install dependencies such as Pillow intentionally.
Private paper content or report-derived details could be included in prompts sent to an image service if the user starts an image-generation step.
Storyboard generation may send paper-derived prompts or visual instructions to an image-generation tool or external provider. The behavior is disclosed and tied to user-requested image steps.
prefer the `imagegen` skill when available. If it is unavailable or insufficient, use ChatGPT Images 2.0 API or another user-approved image-generation API.
Use only approved image providers and avoid sending confidential, unpublished, or restricted paper details unless that sharing is acceptable.
Later storyboards or reports may inherit mistakes or unwanted content from prior project artifacts.
The workflow intentionally reuses uploaded bundles and generated reports across later stages. This is purpose-aligned, but stale, incorrect, or untrusted project content can influence later outputs.
pass forward the uploaded deep-read bundle from Project `sources` so the later stage can reuse the same evidence.
Keep project source bundles controlled, verify the authoritative report before reusing it, and remove unrelated or sensitive files from the project workspace.