No external URLs in skill definition
Vettd coreOWASP LLM07SKILL.md and references/ files do not reference external URLs
Public SkillChecks Passed
anthropics
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
Security Summary
This skill includes a SKILL.md descriptor and ships with scripts. No security concerns were identified.
Source
GitHub
Last Scanned
May 1, 2026
License
Proprietary. LICENSE.txt has complete terms
Category
security
No prompt injection or jailbreak signals detected
Vettd coreScanned text content for instruction override, jailbreak framing, credential solicitation, and embedded injection markers
No secrets or unsafe code patterns detected
Vettd coreScanned all files for credentials, private keys, and code-level risks (eval, shell exec, destructive ops)
Category
best practices
No clear workflow structure
Vettd coreConsider adding numbered steps or a structured procedure for the agent to follow
Skill name collides with well-known skill
Vettd coreOWASP LLM03"pdf" matches a well-known skill name — may cause unintended invocation
Examples included
Vettd coreFound code blocks, input/output samples, or an examples section — concrete samples help agents pattern-match effectively
Progressive disclosure used
Vettd coreSKILL.md body references files in references/, scripts/, or assets/ — agents can load additional context on demand instead of consuming everything upfront
SKILL.md body length is reasonable
Vettd core309 lines (recommended: under 500)
Category
description
Description overclaims scope
Vettd coreBroad trigger words (anything, everything, all files, etc.) widen attack surface — narrow to specific use cases
Description includes usage context
Vettd coreGood: description explains when to activate the skill
Description within character limit
Vettd core437/1024 characters used
Category
evals
No evaluation test cases
Vettd coreAdd an evals/ directory with test prompts and expected outputs to measure skill quality
Category
scripts
scripts/check_bounding_boxes.py: CLI help supported
Vettd coreScript documents its interface via --help or argument parsing
scripts/check_fillable_fields.py: CLI help supported
Vettd coreScript documents its interface via --help or argument parsing
scripts/convert_pdf_to_images.py: CLI help supported
Vettd coreScript documents its interface via --help or argument parsing
scripts/create_validation_image.py: CLI help supported
Vettd coreScript documents its interface via --help or argument parsing
scripts/extract_form_field_info.py: CLI help supported
Vettd coreScript documents its interface via --help or argument parsing
scripts/extract_form_structure.py: CLI help supported
Vettd coreScript documents its interface via --help or argument parsing
scripts/fill_fillable_fields.py: CLI help supported
Vettd coreScript documents its interface via --help or argument parsing
scripts/fill_pdf_form_with_annotations.py: CLI help supported
Vettd coreScript documents its interface via --help or argument parsing
Category
structure
scripts/ directory present
Vettd coreBundled executable scripts found
SKILL.md present
Vettd coreRequired skill definition file found
Valid name field
Vettd coreName "pdf" follows spec (lowercase, hyphens, ≤64 chars)