@abblor/agent-os@0.16.0
Skills, workflows, memory, specs, constitution, hooks, and rules for AI coding agents working on abblor_repos projects.
AI Security Review
scanned 7d ago · by lpm-firewall-aiThe postinstall hook automatically changes a consumer project’s agent setup and may install Git hooks, so this warrants a warning as first-party agent extension setup. The inspected behavior is package-aligned and does not establish credential theft, external payload execution, or broad foreign agent configuration abuse.
Decision evidence
public snapshot- package.json runs the CLI postinstall command during installation.
- The postinstall handler checks for the package in the consumer’s node_modules, then automatically links package content into the project.
- The link operation installs this package’s agent files and may add commit-msg and pre-push Git hooks.
- The SessionStart hook directs agents to read the package’s governance files before working.
- The pre-push hook blocks direct pushes to main and master.
- The flagged graph renderer sends diagram input to a fixed dot command; the brainstorming server defaults to loopback.
- The inspected install path shows no credential transfer or third-party network destination.
- The setup is scoped to this package’s agent materials and project hooks; the source does not establish broad foreign agent configuration abuse.
Source & flagged code
8 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 unpkgPackage source references dynamic require/import behavior.
skills/web-ui/scripts/validate.mjsView on unpkg · L9Findings
Affected versions and remediation
This report applies to @abblor/agent-os@0.16.0.
See all versions of @abblor/agent-os for other recorded verdicts.
- Review the evidence and your use of @abblor/agent-os@0.16.0 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.