sneakoscope@9.2.3
Sneakoscope Codex (`sks`) is an open-source trust layer for Codex CLI and ChatGPT Desktop. It coordinates bounded AI coding agents, records machine-verifiable evidence, preserves project memory, and blocks release claims that are not supported by current
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThe package contains a real lifecycle path that can alter global AI-agent extensions. The path is explicitly opt-in, so blocking as unconsented install-hook abuse is not supported.
Decision evidence
public snapshot- The manifest runs a postinstall lifecycle command.
- The postinstall command imports the installation helper.
- External mutations are gated on SKS_POSTINSTALL_BOOTSTRAP=1.
- When enabled, postinstall invokes global Context7 and Codex skill setup.
- The Context7 setup runs the Codex CLI to add an MCP server.
- The skill setup installs generated skills under the user's global .agents/skills directory.
- The mutation path requires an explicit environment-variable opt-in.
- The Context7 child process clears CODEX_LB_API_KEY from its environment.
Source & flagged code
15 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 contains a possible secret pattern.
dist/core/codex/managed-proxy-env.jsView on unpkg · L43Findings
Affected versions and remediation
This report applies to sneakoscope@9.2.3.
See all versions of sneakoscope for other recorded verdicts.
- Review the evidence and your use of sneakoscope@9.2.3 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.