registry / AI-agent control-surface risk / ai-review-agent
ai-review-agent
Local AI code review swarm — 15 observe-only default agents powered by Ollama, zero API costs (testgen opt-in)
This report shows the evidence for ai-review-agent@1.9.0. 1 of 7 known versions is blocked or flagged. The newest version, 1.15.0, is flagged. See all versions.
AI Security Review
scanned 2mo ago · by lpm-firewall-aiThe lifecycle hook performs persistent global Claude Code command installation, which meets the firewall block boundary for unconsented postinstall mutation of a foreign/broad AI-agent control surface. Local-only LLM networking does not mitigate that install-time control-surface mutation.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
npm postinstall
Impact
Unconsented persistence and expansion of a foreign AI-agent command surface across Claude Code projects.
Mechanism
copies a package-supplied Claude command into the user's home configuration
Policy narrative
On npm postinstall, the package resolves the effective user's home directory, creates ~/.claude/commands, and installs its ai-review.md command without a user command or opt-in. That command is then available to every Claude Code project and grants agent tool permissions to execute package, npm, git, and Ollama commands. This is an unconsented install-time mutation of a foreign, broad AI-agent control surface.
AI rationale
The lifecycle hook performs persistent global Claude Code command installation, which meets the firewall block boundary for unconsented postinstall mutation of a foreign/broad AI-agent control surface. Local-only LLM networking does not mitigate that install-time control-surface mutation.
Evidence
package.jsonscripts/postinstall.mjs.claude/commands/ai-review.mddist/core/llm/ollamaProvider.js~/.claude/commands/ai-review.md
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
- package.json runs postinstall.
- scripts/postinstall.mjs creates ~/.claude/commands and copies ai-review.md there.
- Postinstall targets the invoking sudo user's home when run as root.
- .claude/commands/ai-review.md grants Claude Bash execution for package, npm, git, and Ollama commands.
Evidence against
- The copied command describes user-invoked local review behavior.
- OllamaProvider restricts model requests to localhost/loopback.
- No install-time network request or credential harvesting was found.
Behavioral surface
ChildProcessEnvironmentVarsFilesystemNetworkShell
HighEntropyStringsUrlStrings
Source & flagged code
3 flagged · loading sourcepackage.jsonView file
•scripts.postinstall = node scripts/postinstall.mjs
High
Install Time Lifecycle Scripts
Package defines install-time lifecycle scripts.
package.jsonView on unpkg•scripts.postinstall = node scripts/postinstall.mjs
Medium
Ambiguous Install Lifecycle Script
Install-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgscripts/postinstall.mjsView file
5// and always be runnable with zero build step.
L6: import { existsSync, mkdirSync, copyFileSync } from 'fs'
L7: import { fileURLToPath } from 'url'
...
L31: try {
L32: const source = join(__dirname, '..', '.claude', 'commands', 'ai-review.md')
L33: if (!existsSync(source)) {
...
L38: }
L39: const destDir = join(resolveEffectiveHomeDir(), '.claude', 'commands')
L40: mkdirSync(destDir, { recursive: true })
L41: copyFileSync(source, join(destDir, 'ai-review.md'))
L42: } catch (err) {
Critical
Findings
1 Critical1 High4 Medium4 Low
CriticalAi Agent Control Hijackscripts/postinstall.mjs
HighInstall Time Lifecycle Scriptspackage.json
MediumAmbiguous Install Lifecycle Scriptpackage.json
MediumNetwork
MediumEnvironment Vars
MediumStructural Risk Force Deep Review
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
Affected versions and remediation
This report applies to ai-review-agent@1.9.0.
The versions list below shows the verdict for each recorded version.
- Avoid installing ai-review-agent@1.9.0. 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.
Versions
7 known versions1.15.0latestSuspiciousAgent extension lifecycle riskWarnPublishedAug 28, 2026, 2:48 AM1.14.0Suspicious—WarnUnder ReviewAug 27, 2026, 1:47 PM1.13.1SuspiciousAgent extension lifecycle riskWarnPublishedAug 27, 2026, 12:41 AM1.13.0SuspiciousAgent extension lifecycle riskWarnPublishedAug 23, 2026, 4:09 PM