respecpow@0.9.5
Spec-Powered AI Development Framework - 融合 OpenSpec 规范驱动 + Superpowers 执行引擎的企业级 AI 辅助编程框架(安装即生效版)
AI Security Review
scanned 12d ago · by lpm-firewall-aiThe install lifecycle performs an unconsented write to global AI-agent control settings and installs recurring commands. This meets the policy for blocking install-time AI-agent control-surface mutation.
Decision evidence
public snapshot- The package manifest runs a postinstall script during installation.
- That script modifies global Claude Code and CodeBuddy settings when those tools are present, without a consent prompt.
- The script adds commands that run this package on agent session, prompt, and tool events.
- The named init and update paths concern project-level setup or artifact refresh; the separate CodeGraph installer is reached through initialization.
- The install hook is active package behavior, not an inert payload.
Source & flagged code
8 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgPackage source references child process execution.
dist/core/init/codegraph-step.jsView on unpkg · L11Findings
Affected versions and remediation
This report applies to respecpow@0.9.5.
See all versions of respecpow for other recorded verdicts.
- Avoid installing respecpow@0.9.5. Remove it from direct dependencies and check your lockfile for transitive copies.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
- If this version ran, investigate the affected machine and build environment. Rotate credentials it could access and rebuild from a trusted environment.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.