@seoagent-official/seoagent@1.91.0
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 2mo ago · by lpm-firewall-aiThis is not malicious install-hook behavior, but its explicit agent-control and command-execution capability warrants a warning. The source makes the risky execution user-invoked rather than automatic.
Decision evidence
public snapshot- The init path writes an SEOAgent section into the consumer project's AGENTS.md.
- The explicit process command sends queued work to the Claude Agent SDK with Write, Edit, and Bash enabled under accept-edits mode.
- The CLI synchronizes project state with seoagent.com, creating a remote-to-local agent-workflow channel.
- package.json has no preinstall, install, or postinstall hook.
- The risky agent execution is reachable through an explicit seoagent process command, not package installation or import.
- No secret harvesting, opaque payload loading, or confirmed exfiltration was found.
Source & flagged code
7 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@1.91.0.
See all versions of @seoagent-official/seoagent for other recorded verdicts.
- Review the evidence and your use of @seoagent-official/seoagent@1.91.0 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.