kart-io-picture-book-wizard@1.0.0
VERIFIED· install onlyPublisher claims: "A specialized skill for generating high-quality, consistent children's bilingual picture books using 'banana nano'. Supports 18 visual styles across 4 catego..." 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 2026-11-11 and scored it 89/100 (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
**Rule 1: Registry Check**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- Output Format / 输出格式Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.'Rule 3: Allowed Variations': '**允许的变化**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.'Rule 2: Subsequent Pages Copy Lock Exactly': "**后续页面精确复制锁定**\n\nEvery subsequent\Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.**Rule 2: Arbitrary Name Detection**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.'Rule 4: Physical Consistency Validation': '**物理一致性验证**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.'Rule 1: First Page Establishes Lock': "**第一页建立锁定**\n\nThe first page (or cover\Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.**Rule 3: Celebrity/Fictional Character Detection**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- Output Format / 输出格式Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.To modify an existing character or add a new character:Fix: 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.