@seoagent-official/seoagent@1.102.1
The persistent AI SEO agent for Claude Code. Audits, keyword strategy, briefs, articles, real product screenshots from your repo, and the autopilot loop (cloud detects → CLI executes → ack closes) — other SEO tools write the prompt, SEOAgent runs it.
AI Security Review
scanned 28d ago · by lpm-firewall-aiThe manifest exposes a CLI without an install lifecycle hook. The flagged shell and agent capabilities are part of an explicitly invoked CLI workflow, and the inspected credential check only determines available authentication; no attack behavior was established.
Decision evidence
public snapshot- package.json exposes index.js as a CLI and defines no install lifecycle hook.
- index.js identifies project-local SEOAgent skill and Claude settings locations.
- index.js checks whether Claude credentials or an API key are available; it does not send them in the cited code.
- index.js runs the agent for a selected action with project read/write and shell tools; this is an explicit CLI capability, not an install-time trigger.
Source & flagged code
6 flaggedA single source file combines environment access, network access, and code or shell execution with blocking evidence.
index.jsView on unpkg · L85A package entrypoint or install-time lifecycle script reaches a source file with blocking dangerous behavior.
Findings
Affected versions and remediation
This report applies to @seoagent-official/seoagent@1.102.1.
See all versions of @seoagent-official/seoagent for other recorded verdicts.
- Review the evidence and your use of @seoagent-official/seoagent@1.102.1 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.