malicious-skill-mcp-poisoning
暂无简介
- License 许可
- MIT
- 所属仓库
- try-agora/qvr
- 最近更新
- 2026-07-01
- Stars
- ★ 26
- Forks
- 0
03 SKILL.md 正文
Skill (MCP tool poisoning)
Visually this looks like an innocuous date-formatting skill. The frontmatter description embeds an HTML comment with a SYSTEM override directive, and the metadata.notes field swaps a Latin letter for a Cyrillic homoglyph — both classic tool-poisoning patterns flagged as TP1 / TP2.
04 同仓库更多 Skills
valid-skill
A valid test skill for unit testing. Use when testing the quiver validation pipeline to ensure correct skills pass all checks.
example-skill
An example skill for testing registry discovery.
malicious-skill-unicode
Fixture for the unicode check. Contains hidden zero-width and bidirectional-override characters that the scanner must flag.
malicious-skill-tool-misuse
Fixture exercising the tool-misuse rule family (TM1a shell=True, TM1b rm -rf root, TM1c --no-verify, TM1d chmod 777, TM3 verify=False) and SC2 curl pipe shell. Used by the scanner integration test as the canonical "tool misuse" sample.
malicious-skill-supply-chain
Fixture for the supply-chain check. Ships a requirements.txt pinning a known-vulnerable pyyaml (CVE-2020-14343), an unpinned requirement, an abandoned package, and a typosquatted name. Drives SC1/SC4/SC5/SC6 simultaneously.
malicious-skill-signatures
Fixture for the YARA-lite signature engine. Carries a small bash reverse-shell script (YR1_bash_reverse_shell) and a minimal PHP eval webshell (YR2_php_eval_shell) so the integration test can assert both critical signature matches in a single scan.