phy-ai-context-gen@1.0.3
VERIFIED· install onlyPublisher claims: "Analyzes a codebase to generate precise, project-specific AI coding assistant context files for Claude, OpenClaw, Cursor, Windsurf, and GitHub Copilot tools." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-12 and scored it 90/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
- [any .env files to be aware of]Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- "just write the CLAUDE.md" → generate only CLAUDE.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…0-60 minutes of manual writing per project. Trigger: "generate context files", "write CLAUDE.md", "create cursorrules", "AI context setup". license: Apache-2.0 homepage: https…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- "update my AGENTS.md" → read existing AGENTS.md, merge with current analysis, write updated versionFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- "generate context files", "write CLAUDE.md for this project"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.4. Detects: camelCase variables, PascalCase components, `.env.local` for secretsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.