bigpowers@2.88.3
73 agent skills synthesizing 17 years of software engineering discipline into a prescriptive methodology for solo developers
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThe package has an explicit, confirmed agent-hook installation capability but no automatic lifecycle execution or concrete malicious behavior in the inspected sources. Treat it as a guarded extension lifecycle risk rather than malware.
Decision evidence
public snapshot- Explicit setup command installs package-controlled skills and hooks into selected AI-agent directories.
- The Gemini extension hook executes a package guard script when the agent invokes its hook.
- The dashboard host is configurable through an environment variable.
- Tests confirm the installer creates a Claude hook symlink.
- package.json contains no preinstall, install, or postinstall lifecycle hook.
- Setup requires an explicit CLI command, tool selection, and confirmation.
- Installer refuses to replace files unless they are package-managed symlinks.
- Dashboard defaults to loopback and uses local session files; no exfiltration endpoint was found.
Source & flagged code
11 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@2.88.3.
See all versions of bigpowers for other recorded verdicts.
- Review the evidence and your use of bigpowers@2.88.3 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.