No security findings. Scanned 2 times, most recently 2026-02-01.
Second scanner: NVIDIA SkillSpector
Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
- Package
- 12 files, 63 KB
- SKILL.md
- 836 words, 12+ sections
- Code
- Python (8)
- License
- Proprietary. LICENSE.txt has complete terms
SKILL.md covers: PDF Processing Guide · Overview · Quick Start · Read a PDF · Extract text · Python Libraries · pypdf - Basic Operations · pdfplumber - Text and Table Extraction · Combine all tables · reportlab - Create PDFs · Add text · Add a line
Findings
No findings. SAFE
What is in the package
| File | Kind | Size |
|---|---|---|
LICENSE.txt | doc | 1.4 KB |
SKILL.md | doc | 6.9 KB |
forms.md | doc | 9.2 KB |
reference.md | doc | 16 KB |
scripts/check_bounding_boxes.py | script | 3.1 KB |
scripts/check_bounding_boxes_test.py | script | 8.6 KB |
scripts/check_fillable_fields.py | script | 362 B |
scripts/convert_pdf_to_images.py | script | 1.1 KB |
scripts/create_validation_image.py | script | 1.6 KB |
scripts/extract_form_field_info.py | script | 6.0 KB |
scripts/fill_fillable_fields.py | script | 4.7 KB |
scripts/fill_pdf_form_with_annotations.py | script | 3.5 KB |
External hosts referenced
www.anthropic.com github.com opensource.adobe.com westhealth.github.io
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Package contents recorded 2026-10-22 at commit 69c0b1a06741. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
- Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Scan history
| Date | Verdict | Findings | Change | Analyzers | Raw |
|---|---|---|---|---|---|
| SAFE | 0 | = | static behavioral llm trigger meta | JSON | |
| SAFE | 0 | first scan | static behavioral llm trigger | JSON |
Sources
- Repository: https://github.com/anthropics/skills/tree/main/skills/pdf
- Raw scan result: skills-pdf-scan.json
- Badge for your README:
- Request a re-scan