creator/Anthropic-Cybersecurity-Skills
1
0
Fork 0
mirror of https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git synced 2026-08-03 09:20:18 +03:00
Code Issues Packages Projects Releases Wiki Activity

Rewrite 548 skill descriptions to the activation rubric

Browse Source 
Each rewritten description now states both what the skill does (concrete
capability, named tools/artifacts) and an explicit when-to-use trigger,
improving agent discovery/activation. Grounded in each skill's own body;
changes confined to the `description` field only (bodies and all other
frontmatter untouched). Produced by a gated audit->rewrite->recheck loop
(548 -> 0 flagged) with a sampled anti-invention check (0 ungrounded).

Schema: 817/817 pass. Framework-ID gate: 0 defects.
This commit is contained in:
Mahipal
2026-08-02 09:32:13 -07:00
parent 04a207702e
commit 2fb6a9faff
548 changed files with 2189 additions and 1915 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skills/performing-jwt-none-algorithm-attack/SKILL.md
+5 -2
View File
@@ -1,7 +1,10 @@
---
name: performing-jwt-none-algorithm-attack
description: Execute and test the JWT none algorithm attack to bypass signature verification
by manipulating the alg header field in JSON Web Tokens.
description: Execute and test the JWT none algorithm attack, crafting tokens with
the alg header set to none using PyJWT and an intercepting proxy (Burp Suite/mitmproxy)
to bypass signature verification and forge arbitrary claims. Use during authorized
penetration tests or security assessments of applications that use JWT for authentication
or authorization, to validate that the server rejects unsigned tokens.
domain: cybersecurity
subdomain: api-security
tags: