Add optional HOL Guard runtime enforcement to AI Agent security skill - #4
Open
kantorcodes wants to merge 1 commit into
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds an optional HOL Guard local runtime boundary to the maintained
ai-agent-securityskill and its Cursor mirror before high-risk agent tool execution.The new section installs and invokes the real HOL Guard CLI, derives the exact supported harness from
hol-guard detect --json, then uses bootstrap → install → protected dry-run → guarded run → harness doctor/status. Deny, review-required, error, timeout, or unproven protection stops mutation-bearing work instead of falling back to an unprotected agent.Boundary
HOL Guard is additive to the existing security guidance. It does not replace authentication, authorization, human confirmation/review, sandboxing, or target-service server-side controls, and the text does not claim HOL Guard runs inside third-party services.
Validation
skills/ai-agent-security/SKILL.mdand its maintained.cursormirrorgit diff --checkpassesmasterAffiliation: I maintain HOL Guard / Hashgraph Online. AI assistance was used to prepare this focused contribution; I checked the submitted diff and runtime-boundary claims against the current HOL Guard skill/source before opening the PR.