feat: security-review agent — reusable skill + CLI assessment - #131
Merged
Conversation
Adds a fully packaged security-review agent following the AgentFactory 5-directory standard. The agent's skill generates or updates dated REVIEW-SECURITY-ARCHITECTURE-YYYY-MM-DD.md reports covering: component status matrix, 7 Mermaid diagrams, SEV-classified security findings, design gaps, and a prioritised recommendations table. CLI-ASSESSMENT.md documents observations from the live deploy→wrap→import lifecycle used to transfer this agent to agentfactory-harness, including 9 gaps found during actual execution (triggers split, --version missing, --project-root CWD resolution, audit pre-sync requirement, etc.). Co-Authored-By: 🤖Factory <noreply@agentfactory.dev>
Co-Authored-By: 🤖Factory <noreply@agentfactory.dev>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
security-reviewagent following the 5-directory AgentFactory standardskills/security-review/withSKILL.md,skill-manifest.json, and tworeferences/filessecurity-review-v1.0.0.zipand transfers it toagentfactory-harnessvia the CLIdocs/CLI-ASSESSMENT.mdwritten from 9 live observations during the transfer lifecycleWhat the skill does
Generates or updates a dated
docs/REVIEW-SECURITY-ARCHITECTURE-YYYY-MM-DD.mdon any TypeScript/Python/Go repo, covering:Supports two modes: new (fresh dated report) and update (delta on same branch, version bumped, fixed items struck through).
CLI Assessment highlights (from live execution)
5 gaps surfaced during the transfer:
--versionnot defined on root grouptriggersnot propagated fromSKILL.mdtoskill-manifest.json--project-rootresolves against CWD before applying the flagauditrequires manualsyncfirst (unlikewrap)status,upgrade, or--dry-runcommandsFull details in
docs/CLI-ASSESSMENT.md.Test plan
agentfactory-gen audit security-reviewexits 0agentfactory-gen wrap security-reviewproduces ZIP with 6 filesagentfactory-gen briefshowssecurity-reviewin skill tableagentfactory-harnesshas.ai/skills/security-review/and.ai/agents/security-review//security-reviewinvocation in Claude session loads the skill🤖 Generated with Claude Code