bigpowers@2.88.0
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-aiThis is not malicious install-hook abuse because npm installation has no lifecycle trigger and the changes require an explicit interactive command. The package still installs behavior-bearing hooks into agent control surfaces, so it warrants a warning.
Decision evidence
public snapshot- The explicit setup command links a Gemini extension and several hook executables into the user’s global agent configuration.
- A session-start hook runs a project survey and injects its output into agent context.
- The package also includes an environment-configurable local dashboard server.
- package.json has no preinstall, install, postinstall, or prepare lifecycle hook.
- The configuration changes require an interactive user-invoked setup command.
- Inspected hooks guard commands or manage context; no credential collection, external exfiltration, or hidden payload execution was found.
- The dashboard defaults to 127.0.0.1 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@2.88.0.
See all versions of bigpowers for other recorded verdicts.
- Review the evidence and your use of bigpowers@2.88.0 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.