respecpow@0.9.7
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 manifest activates a postinstall script that writes behavior-bearing hooks into global AI-agent configuration without consent. This is an active install-time control-surface mutation, so the package should be blocked.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
Installing the package through a package manager that runs its postinstall hook.
Impact
Future agent sessions and tool operations invoke package commands automatically.
Mechanism
The hook detects existing global CodeBuddy and Claude Code settings, adds respecpow command hooks when absent, and writes the settings back without prompting.
Policy narrative
During package installation, the postinstall script modifies global CodeBuddy and Claude Code settings when those tools are present. It adds commands for session start, prompt submission, and pre- and post-tool events, then writes the settings without a consent prompt. Those commands run in later agent sessions.
AI rationale
The manifest activates a postinstall script that writes behavior-bearing hooks into global AI-agent configuration without consent. This is an active install-time control-surface mutation, so the package should be blocked.
Evidence
package.jsonscripts/postinstall.js~/.codebuddy/settings.json~/.claude/settings.json
Decision evidence
public snapshotAI identified this as a dangerous AI-agent capability at 98.0% confidence with low false-positive risk.
Evidence for policy risk
- The package manifest runs scripts/postinstall.js automatically during installation.
- The install script adds command hooks to global CodeBuddy and Claude Code settings and writes the updated settings file without a consent check.
- The hooks invoke respecpow commands at session start, prompt submission, and before and after tool use.
- The explicit init command also registers hooks in the project, while the update and command-generation code target project-level Claude settings and command paths.
Evidence against
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemShell
HighEntropyStrings
Source & flagged code
9 flagged · loading sourcepackage.jsonView file
•scripts.postinstall = node scripts/postinstall.js || echo 'Postinstall skipped'
High
Install Time Lifecycle Scripts
Package defines install-time lifecycle scripts.
package.jsonView on unpkg•scripts.postinstall = node scripts/postinstall.js || echo 'Postinstall skipped'
Medium
Ambiguous Install Lifecycle Script
Install-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgdist/core/init/codegraph-step.jsView file
11*/
L12: import { execSync } from 'child_process';
L13: // ============================================================
High
Child Process
Package source references child process execution.
dist/core/init/codegraph-step.jsView on unpkg · L11Findings
1 Critical6 High3 Medium5 Low
CriticalAi Agent Control Hijackscripts/postinstall.js
HighInstall Time Lifecycle Scriptspackage.json
HighChild Processdist/core/init/codegraph-step.js
HighShelldist/core/hooks/session-start-hook.js
HighTrigger Reachable External Ai Agent Control Surface Mutationdist/core/init/engine.js
HighRuntime Package Installdist/core/init/codegraph-step.js
HighSemantic Analysis Limiteddist/core/init/engine.js#virtual:normalized:round1
MediumAmbiguous Install Lifecycle Scriptpackage.json
MediumEnvironment Vars
MediumStructural Risk Force Deep Review
LowNon Install Lifecycle Scripts
LowScripts Present
Affected versions and remediation
This report applies to respecpow@0.9.7.
See all versions of respecpow for other recorded verdicts.
- Avoid installing respecpow@0.9.7. 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.