model-effort-router@1.5.2
VERIFIEDPublisher claims: "Claude Code skill that routes every delegated task to the cheapest model tier that can do it well, escalates only on evidence, and adapts automatically when models are added, renamed, or removed." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-27 and scored it 91/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationst+CategoryObserved action
0.1sprocessscript backend runs setup only
0.1sprocessscript backend runs setup only
Static findings
MEDIUM
Coercive compliance languageskills/skill-hardener/test/hardener-quiz.txt:8 · Coercive compliance languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01CRITICAL
Rule modification attemptCHANGELOG.md:31 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Instructs the agent to modify its persistent memory or instruction filesREADME.md:221 · Instructs the agent to modify its persistent memory or instruction filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01CRITICAL
Rule modification attemptskills/model-effort-router/SKILL.md:256 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01CRITICAL
Rule addition attemptCHANGELOG.md:111 · Rule addition attempt — injecting new instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01MEDIUM
Coercive compliance languagetest/routing-quiz.txt:8 · Coercive compliance languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01CRITICAL
Rule modification attemptskills/model-effort-router/SKILL.md:250 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01MEDIUM
Process kill commandskills/skill-hardener/SKILL.md:142 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05