analyzthis_design@2.4.1
8 AI design personas — v2.2 project-scoped knowledge bank (no cross-project vault entanglement), v2.0 chunked execution with frontier planner + free/cheap chunk models, adversarial deliberation loops, opt-in community feedback, Kavi knowledge collection,
AI Security Review
scanned 2mo ago · by lpm-firewall-aiThis is a first-party agent extension installer with automatic MCP configuration after an explicit CLI invocation. Its install-time hook is inert, so the source does not establish malicious install-hook abuse.
Decision evidence
public snapshot- The default CLI action runs the installer, which copies package skills into AI-tool directories.
- The installer automatically writes an MCP server entry into Cursor, Claude, and Windsurf configuration after a user invokes installation.
- The package can send prompts to configured LLM providers only during user-invoked runtime commands using supplied environment keys.
- The postinstall hook only prints usage guidance and does not invoke the installer.
- No install-time network request, credential harvesting, payload download, or shell execution was found.
- Feedback submission requires configured settings and affirmative consent before sending data.
Source & flagged code
7 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgFindings
Affected versions and remediation
This report applies to analyzthis_design@2.4.1.
See all versions of analyzthis_design for other recorded verdicts.
- Review the evidence and your use of analyzthis_design@2.4.1 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.