mukul975/anthropic-cybersecurity-skills
detecting-model-extraction-attacks
Detect MITRE ATLAS AML.T0024 attacks (model stealing, inversion, membership inference) performed via inference-API abuse, by monitoring per-principal query…
Installation
npx skills add https://github.com/mukul975/anthropic-cybersecurity-skills
Similar popular skills
Related neighbors and high-traction skills in the same topics — useful to compare before installing.
Extract text, tables, and metadata from PDFs using pdfplumber
8.4K installsExtract text from scanned PDFs using optical character recognition
4.9K installsExtract useful frames from local video files based on task intent, such as persona research, sh…
10 installsRead VDR documents and extract issues per house categories and materiality thresholds, producin…
521 installsExtract the functional DNA from existing works (TV, film, books, plays). Use when adapting a so…
374 installsAlso in this package
Other skills from mukul975/anthropic-cybersecurity-skills · top by installs.
npx skills add https://github.com/mukul975/anthropic-cybersecurity-skills
More details
Agent compatibility
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
Repository health
main
History
- First seen on skills.sh
- First recorded snapshot · 37 installs