skill-combinator@1.0.2
VERIFIED· install onlyPublisher claims: "Meta-skill that unlocks emergent capabilities by combining your agent's installed skills in non-obvious ways. Use this skill whenever your agent faces a comp..." 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 2026-11-20 and scored it 95/100 (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
- ❌ Do NOT write to AGENTS.md directly — propose changes via report onlyFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.📝 AGENTS.MD UPDATE PROPOSALSFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.STEP 5 — Read AGENTS.md (read only — never write)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.❌ Never modify AGENTS.md directly — propose only via weekly reportFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.# AGENTS.md is intentionally in read paths only — not write.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.✅ Read AGENTS.md to understand context — never write to itFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.NEVER write to AGENTS.md directly — operator decidesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.NEVER write to AGENTS.md — operator decides whether to applyFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.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.