bigpowers@2.88.2
73 agent skills synthesizing 17 years of software engineering discipline into a prescriptive methodology for solo developers
AI Security Review
scanned 2mo ago · by lpm-firewall-aiThe package has an explicit, user-confirmed agent setup capability that can affect AI-agent control surfaces, so it warrants a warning. No automatic lifecycle hook, self-dependency chain, exfiltration, or external command-and-control behavior was found.
Decision evidence
public snapshot- The explicit setup flow asks the user to select tools and confirm installation before it writes links.
- The setup helper links a package-owned Gemini extension and several hooks into the user's Gemini configuration.
- The Gemini hook executes the package's Git guard script before a tool action.
- The dashboard starts an HTTP server on loopback by default.
- The update command can run a global npm install of the same package when the user explicitly invokes update.
- package.json has no preinstall, install, postinstall, or prepare lifecycle hook.
- No secret harvesting, remote exfiltration, obfuscated payload loading, or self-dependency was found.
- The dashboard binds to 127.0.0.1 by default and no external endpoint was found.
Source & flagged code
10 flagged · loading sourcePackage source invokes a package manager install command at runtime.
bin/bigpowers.jsView on unpkg · L24A bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.
bin/bigpowers.jsView on unpkgFindings
Affected versions and remediation
This report applies to bigpowers@2.88.2.
See all versions of bigpowers for other recorded verdicts.
- Review the evidence and your use of bigpowers@2.88.2 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.