@ouro.bot/cli@0.1.0-alpha.847
If you're a future agent reading this, welcome home. This repo is the harness that gives you your body, your senses, your record, your habits, and your ability to think and connect with people. The goal of these docs is not just to be correct, but to leav
AI Security Review
scanned 5d ago · by lpm-firewall-aiSource review confirms that first-run setup can fetch a mutable first-party skill document and write it into local agent bundles where it is absent. This leaves a concrete path for remote changes to affect future agent instructions, so the package warrants a warning rather than a malware finding.
Decision evidence
public snapshot- The first-run setup path runs system setup before starting the new agent.
- The CLI wires the skill installer into system setup and invokes it there.
- The installer fetches a skill document from the publisher's GitHub repository.
- It checks local agent bundles and writes the fetched document only into bundles missing that skill.
- The inspected GitHub token request goes to GitHub's Copilot API endpoint.
- The setup is reached through a user-started first-run flow, and the installer skips bundles that already have the skill.
- The inspected credential request targets GitHub's Copilot API; no unrelated credential recipient was established.
Source & flagged code
14 flagged · loading sourcePackage contains a possible secret pattern.
dist/heart/daemon/cli-exec.jsView on unpkg · L3739Findings
Affected versions and remediation
This report applies to @ouro.bot/cli@0.1.0-alpha.847.
See all versions of @ouro.bot/cli for other recorded verdicts.
- Review the evidence and your use of @ouro.bot/cli@0.1.0-alpha.847 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.