bigpowers@2.88.6
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-aiStatic inspection shows an interactive agent-skill installer rather than an automatic lifecycle payload. The flagged runtime npm command is limited to an explicit global update action, and the dashboard defaults to loopback.
Decision evidence
public snapshot- The manifest has no npm lifecycle hook; its setup command is user-invoked.
- The update path runs npm only after an explicit update command and global-install check.
- Setup asks the user to confirm before installing to selected runtimes.
- The installer refuses to replace destinations unless they are package-managed symlinks.
- The Gemini hook only delegates to the packaged git guard.
- The dashboard defaults to a loopback address and local session directory.
- No install-time execution, self-dependency, secret harvesting, or exfiltration was found.
- The AI-agent configuration changes are part of an interactive, user-selected setup flow.
- The local HTTP server is not an external network endpoint by default.
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@2.88.6.
See all versions of bigpowers for other recorded verdicts.
- Review the evidence and your use of bigpowers@2.88.6 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.