@seoagent-official/seoagent@1.108.5
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 scanner’s command-execution and network findings do not establish command-output exfiltration: the inspected shell calls check Claude availability and credential status. The explicit setup does install recurring agent hooks, warranting a warning under the agent integration policy.
Decision evidence
public snapshot- The CLI entrypoint is `index.js`; no install lifecycle hook is declared in `package.json`.
- The `init` command calls setup code that adds a recurring sync command to Claude Code session and write/edit hooks in `.claude/settings.json`.
- The setup is package-owned agent integration, so it carries lifecycle risk; the inspected source does not establish unconsented install-time mutation or a concrete attack.
- The hook setup is reached through the explicit `init` command rather than an npm install hook.
- The inspected shell calls check for Claude and inspect local credential status; their output is not sent over the network.
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 · L87A 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@1.108.5.
See all versions of @seoagent-official/seoagent for other recorded verdicts.
- Review the evidence and your use of @seoagent-official/seoagent@1.108.5 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.