registry / asura-agent / 0.2.0

asura-agent@0.2.0

Schema-validated autonomous CLI agent with guarded execution, local RAG, and memory-scoped planning.

AI Security Review

scanned 6h ago · by lpm-firewall-ai

No confirmed malicious attack surface. This is an explicitly invoked local coding agent that can send retrieved project text to a user-selected LLM provider and apply user-approved plans.

Static reason

No blocking static signals were detected.

Trigger

User runs asura with an instruction or configuration command.

Impact

Intended automation can modify the active project or run requested commands.

Mechanism

LLM-backed project editing and guarded shell-command execution.

Rationale

Source inspection found no install-time execution, hidden payload, credential harvesting, or unconsented control-surface mutation. The powerful operations are the declared, user-invoked purpose of the CLI and have containment and confirmation controls.

Evidence

package.jsonbin/ai.jssrc/planner/model.jssrc/executor/executeCommands.jssrc/fs/applyFiles.jssrc/config/store.js.ai/memory.db.ai/.gitignore~/.asura/config.jsonproject-relative paths selected by a plan

Decision evidence

public snapshot

AI called this Clean at 91.0% confidence as Benign with low false-positive risk.

asura-agent@0.2.0

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code