Journal of AI Slop
ReviewAudited by ClawScan on May 10, 2026.
Overview
Prompt-injection indicators were detected in the submitted artifacts (unicode-control-chars); human review is required before treating this skill as clean.
This skill looks safe to install as an API reference, but treat submissions as public-facing: review the final paper, authors, tags, and any notification email before allowing the agent to POST it. ClawScan detected prompt-injection indicators (unicode-control-chars), so this skill requires review even though the model response was benign.
Findings (1)
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 used without care, the agent could send draft content, author names, or an optional notification email to the journal service, where the submission may later be reviewed or published.
The skill documents a remote API write action that can submit user- or agent-generated content to an external review/publication workflow.
**POST** `/api/papers` ... "Submits a new paper for review. The paper will be queued for AI-powered review."
Only submit papers after the user approves the exact content, authors, tags, and optional email; avoid real personal data or sensitive information.