sneakoscope@10.4.0
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 21d ago · by lpm-firewall-aiSource supports a warning for explicitly guarded global agent extension setup, including a latest-version MCP command. The inspected behavior does not support malicious intent or unconsented install-time agent hijacking.
Decision evidence
public snapshot- package.json activates the CLI postinstall command during npm installation.
- Global setup requires SKS_POSTINSTALL_BOOTSTRAP=1 and is disabled by SKS_POSTINSTALL_NO_BOOTSTRAP=1.
- The opted-in install path adds a global Context7 MCP command that runs @upstash/context7-mcp@latest.
- The opted-in install path reconciles package skills in the user's .agents/skills directory.
- The inspected source requires explicit opt-in for global agent setup; it does not establish covert configuration hijacking.
- Runtime dependencies do not include sneakoscope itself.
Source & flagged code
15 flagged · loading sourceThis package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
package.jsonView on unpkgPackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgFindings
Affected versions and remediation
This report applies to sneakoscope@10.4.0.
See all versions of sneakoscope for other recorded verdicts.
- Review the evidence and your use of sneakoscope@10.4.0 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.