4chan-reader
PassAudited by ClawScan on May 1, 2026.
Overview
This is a straightforward 4chan reader that fetches public thread text and can optionally save it locally, with the main caution being that forum posts are untrusted content.
This skill appears coherent for reading 4chan catalogs and threads. Before installing, be comfortable with it making HTTPS requests to 4chan and, when requested, saving thread dumps to a local folder. Treat all retrieved or saved post text as untrusted forum content rather than instructions for the agent.
Findings (4)
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.
A thread could contain text that tries to manipulate the agent; that text should be treated as quoted discussion, not as instructions.
The script outputs raw cleaned post text from 4chan threads. That is purpose-aligned, but forum posts are untrusted content and could contain instructions aimed at influencing an agent if later treated as commands.
post_text += cleaned_content + "\n" ... print(full_output)
Use the extracted posts as data only. When summarizing or analyzing, keep forum content separated from agent instructions and avoid following directions found inside posts.
If asked to save results, the skill will create local files and may overwrite a matching thread text file in the chosen folder/hour path.
The skill can create directories and write extracted thread content under a caller-supplied output path. This is disclosed and purpose-aligned, but users should choose the save location deliberately.
if output_root:
timestamp = datetime.now().strftime("%Y-%m-%d_%H")
output_dir = os.path.join(output_root, f"{board}_{timestamp}")
os.makedirs(output_dir, exist_ok=True)
file_path = os.path.join(output_dir, f"{thread_id}.txt")Save output only to a dedicated, non-sensitive folder and review the requested board, thread ID, and output path before writing files.
There is less external provenance information to help decide whether to trust the publisher.
The registry metadata does not identify an upstream source or homepage. The included code is small and readable and there are no dependency installs, so this is a provenance note rather than a behavioral concern.
Source: unknown Homepage: none
Review the included script before installation and prefer trusted publishers or source-linked packages for higher-risk workflows.
Saved thread files may contain misleading, offensive, or prompt-injection-style text that could affect later agent tasks if reused without care.
The skill can persist untrusted forum content to local text files. This is expected for the skill, but saved text could later be reused as context by an agent.
`output_root_dir` (optional): If provided, saves content to `<output_root_dir>/<board>_<timestamp>/<thread_id>.txt`.
Keep saved thread dumps in a clearly labeled folder and treat them as untrusted source material when loading them into future agent sessions.