Skip to content

Add SkillWatch to Tools & Frameworks#31

Open
kuzivaai wants to merge 1 commit into
LLMSecurity:mainfrom
kuzivaai:add-skillwatch
Open

Add SkillWatch to Tools & Frameworks#31
kuzivaai wants to merge 1 commit into
LLMSecurity:mainfrom
kuzivaai:add-skillwatch

Conversation

@kuzivaai

Copy link
Copy Markdown

Adds SkillWatch to Tools & Frameworks.

SkillWatch periodically re-checks the external URL content that AI skills and MCP tools reference and flags suspicious changes — the post-review "bait-and-switch" where a referenced page is swapped after a scan passes. It also keeps an append-only, hash-chained content ledger with optional external anchoring (RFC 3161 timestamp or a git commit), so a rewrite of the recorded history is detectable.

  • Open source (Apache-2.0), on PyPI (pip install skillwatch), local CLI, SARIF output.
  • Actively maintained — v0.3.0 released today; CI green on Python 3.10–3.13.
  • Complements static scanners: it monitors referenced content over time rather than scanning skill code at install.

Honest scope: the change-triage is regex-based and best-effort (it publishes its own measured recall/precision), not a guarantee.

🤖 Generated with Claude Code

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant