paper-image-extractor
Extract figures from papers — prioritizes arXiv source package for high-quality images
57
66%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./skills/paper-image-extractor/SKILL.mdE005: Suspicious download URL detected in skill instructions.
What this means
Detected a suspicious URL in the skill instructions that could lead the agent to download and execute malicious scripts or binaries. This includes links to executables from untrusted sources, typosquatting of official packages, URL shorteners that obscure the destination, and personal file hosting services.
Why it was flagged
The arXiv e-print endpoints are official and low-risk, but the GitHub URL (https://github.com/evil-read-arxiv) points to an unknown/suspicious username that could host untrusted code or releases and is therefore flagged.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
In `scripts/extract_images.py`, the runtime path downloads the arXiv source tarball from `https://arxiv.org/e-print/{arxiv_id}` and then unpacks and scans for image files/directories, thereby ingesting outsider-authored free text that exists inside the arXiv-submitted source archive (e.g., files in `pics/`, `figures/`, root, and nested PDFs).
- Repository
- OpenLAIR/dr-claw
- Commit
d51b64e
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.