@the-open-engine-company/zeroshot@10.18.0
Enforces your team's QA process on coding agents. Define the workflow as a graph of implementers, reviewers, tests and repair loops; every task runs through it and no agent can skip a step. Works with Codex, Claude Code, GitHub Copilot and Pi.
AI security review
scanned · by lpm-firewall-aiThe postinstall hook automatically installs package-owned skills into agent configuration directories, which warrants a warning under the agent extension lifecycle policy. The inspected behavior does not support a malicious verdict.
Decision evidence
public snapshot- The package runs install.js from its postinstall hook.
- The install flow installs the package’s own skills after installing its executable.
- Those skills are written under the user’s shared agent skills directory and Claude Code skills directory.
- The install also downloads release artifacts from the project’s GitHub releases.
- The inspected source shows first-party skill installation, with checks that avoid replacing non-managed files or symlinks.
- github.com
Findings
1 critical · 1 high · 6 medium · 4 lowWhere they are, most severe file first. Code opens a file's flagged lines, with their evidence, below.
lib/skills.js1 criticalpackage.json1 high · 2 mediuminstall.js1 mediumShow all 12 findings
lib/skills.js1 findingpackage.json3 findingsinstall.js1 findingSource & flagged code
5 flaggedPackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgShared scanner record · 2 findings · 1 line
The package runs install.js from its postinstall hook.
package.jsonView on unpkg · L30Code excerpt · 7 lines
Source creates an unconsented AI-agent control surface through install-time mutation or a default unauthenticated remote skill channel.
lib/skills.jsView on unpkg · L32Code excerpt · 16 lines
The package runs install.js from its postinstall hook.
install.jsView on unpkg · L7Code excerpt · 3 lines
Affected versions and remediation
This report applies to @the-open-engine-company/zeroshot@10.18.0.
See all versions of @the-open-engine-company/zeroshot for other recorded verdicts.
- Review the evidence and your use of @the-open-engine-company/zeroshot@10.18.0 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.