bigpowers@2.87.6
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 no automatic npm lifecycle trigger or concrete malicious behavior. Its explicit installer still creates persistent, behavior-bearing agent integrations, so it warrants a warning rather than a publish block.
Decision evidence
public snapshot- The explicit setup flow can install package-owned skills and hooks into selected AI tool directories.
- The Gemini session-start hook executes a project survey and supplies its output as additional agent context.
- The CLI update command can run npm to replace a global installation with the latest release.
- package.json has no preinstall, install, or postinstall lifecycle script.
- Setup requires interactive scope, tool selection, and a confirmation before it writes links.
- The installer refuses to replace files unless they are already bigpowers-managed symlinks.
- The dashboard binds to loopback by default and no external endpoint or exfiltration code was found.
Source & flagged code
11 flagged · loading sourceThis package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
bin/bigpowers.jsView on unpkgPackage source invokes a package manager install command at runtime.
bin/bigpowers.jsView on unpkg · L24Findings
Affected versions and remediation
This report applies to bigpowers@2.87.6.
See all versions of bigpowers for other recorded verdicts.
- Review the evidence and your use of bigpowers@2.87.6 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.