focalapi-cli@1.1.3
让任意 AI Agent 直接调用 focalapi 创作模型的命令行工具
AI Security Review
scanned 23d ago · by lpm-firewall-aiThe automatic hook installs package-owned agent skills without prompting, which warrants a warning under the first-party extension policy. Inspected behavior does not establish malware or a block-eligible attack.
Decision evidence
public snapshot- package.json activates scripts/postinstall.cjs after npm installation.
- The hook invokes connect install automatically, without a consent prompt.
- The CLI selects detected agent skill directories and replaces bundled skill destinations.
- Installation is limited to focalapi-prefixed skills, supporting a first-party extension lifecycle warning.
- The bundled router directs agents to use FocalAPI for creative tasks.
- No concrete credential theft or remote payload execution was identified.
- Skill installation uses staging, backups, rollback, and a package-owned manifest.
- The update command checks versions without automatically upgrading.
Source & flagged code
6 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgFindings
Affected versions and remediation
This report applies to focalapi-cli@1.1.3.
See all versions of focalapi-cli for other recorded verdicts.
- Review the evidence and your use of focalapi-cli@1.1.3 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.