kai-report-creator@1.23.3
VERIFIED· install onlyPublisher claims: "Use when the user wants to CREATE or GENERATE a report, business summary, data dashboard, or research doc — 报告/数据看板/商业报告/研究文档/KPI仪表盘. Handles Chinese and Eng..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 8 of 14 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · 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 (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 and scored it 81/100 (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 · 1 s · 2 scenarios · 0 deviationsStatic findings
completed = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.mod = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Edit mode (always present)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.completed = subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.return subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.CDN libraries (add only what's needed; omit if --bundle, inline instead)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.if importlib.util.find_spec("playwright") is None:Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.return subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.cleanup_completed = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.Export (always present)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.❌ Never put long units directly as plain text contentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.Summary card overlay (always present) — left+right panels injected by buildCard()Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.spec.loader.exec_module(module)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.❌ Never combine data-target-value with kpi-suffix span — countUp will overwrite the spanFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.module = importlib.util.module_from_spec(spec)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.spec.loader.exec_module(mod)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.https://github.com/kaisersong/kai-report-creator/archive/refs/tags/v1.23.3.zipFix: Pin versions and sources; vendor anything fetched at install time.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.