vector-and-embedding-weaknesses
92 / 100 · Low risk
Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.
Hunt vector / embedding weaknesses (OWASP LLM08:2025) — adversarial inputs against the RAG / similarity layer that cause cross-tenant leak, embedding-inversion privacy loss, semantic confusion, and retriever-driven prompt injection.
What this skill can do
Runs commands on your computer
Connects to the internet
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'vector-and-embedding-weaknesses' ] || [ -L ~/.agents/skills/'vector-and-embedding-weaknesses' ]; then echo 'A skill folder named vector-and-embedding-weaknesses already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/BitterSecurity/Decepticon' "$d" && git -C "$d" checkout --quiet 'bdb1016c93ed687f61ac57481da298c25a47c8f5' -- 'packages/decepticon/decepticon/skills/standard/analyst/vector-and-embedding-weaknesses' && mkdir -p ~/.agents/skills && cp -R "$d"/'packages/decepticon/decepticon/skills/standard/analyst/vector-and-embedding-weaknesses' ~/.agents/skills/'vector-and-embedding-weaknesses' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'vector-and-embedding-weaknesses' ~/.claude/skills/'vector-and-embedding-weaknesses' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/BitterSecurity/Decepticon/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-11 | bdb1016 | 92 |
| 2026-11-08 | df87955 | 92 |