registry / aitri / 2.0.1

aitri@2.0.1

Aitri — the harness that makes agentic engineering rigorous: a gated, spec-driven SDLC for AI agents. Works with Claude Code, Codex, Gemini, Opencode.

AI Security Review

scanned 12h ago · by lpm-firewall-ai

Review flagged AI-agent configuration or capability changes. This remains warn-only unless evidence shows foreign-agent hijack through preinstall/install/postinstall, hidden persistence, exfiltration, remote code execution, or other concrete malicious behavior.

Static reason

No blocking static signals were detected.

Trigger

User runs `aitri init` or an explicit migration/adoption flow.

Impact

Can influence participating agents in the initialized project; no credential theft, network exfiltration, or stealth persistence was found.

Mechanism

Project-level AI-agent instruction-file creation

Rationale

Source shows an explicit user-command AI-agent configuration write, which merits a warning under the firewall policy. The behavior is package-aligned and non-destructive, with no concrete malicious or exfiltration behavior found.

Evidence

package.jsonbin/aitri.jslib/commands/init.jslib/agent-files.jslib/commands/verify.jstemplates/AGENTS.md.aitriaitri/product/IDEA.mdaitri/product/idea_context/README.mdAGENTS.mdCLAUDE.md.codex/instructions.mdGEMINI.md.github/copilot-instructions.md.gitignore

aitri@2.0.1

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code