Skills/ClawHub/kai-report-creator

kai-report-creator@1.23.3

VERIFIED· install only

Publisher 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.

Registry ClawHubPublisher kaisersong · publishing for 187 daysInstalls 2,136Last detonated 15 min ago
$clawhub install kai-report-creator
WatchReport an issue

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 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessexec /usr/bin/dirname
0.1sprocessexited 1: /usr/bin/python3: No module named pytest
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 2: compare-skill-eval-baseline.py: error: the following arguments are required: --old, --new
0.3sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.4sprocessbundled script run in the sandbox with no arguments
0.4sprocessexited 2: export-image.py: error: the following arguments are required: html
0.4sprocessbundled script run in the sandbox with no arguments
0.5sprocessexited 2: guard_validate.py: error: the following arguments are required: ir_path
0.5sprocessbundled script run in the sandbox with no arguments
0.6sprocessexited 2: html_quality_gate.py: error: the following arguments are required: html_path
0.6sprocess8 of 14 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.6sprocessscript backend runs setup only
0.6sprocessscript backend runs setup only
0.6sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedscripts/verify-release.py:216 · Python subprocess execution detectedcompleted = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_guard_integration.py:136 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_skill_eval_baseline_compare.py:56 · Python subprocess execution detectedreturn subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
LOW
Dynamic module loadingtests/conftest.py:17 · Dynamic module loadingmod = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
HTML comment carrying imperative instructions to the agentreferences/html-shell/toc-edit-summary.md:49 · HTML comment carrying imperative instructions to the agentEdit mode (always present)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Python subprocess execution detectedscripts/run-skill-evals.py:543 · Python subprocess execution detectedcompleted = subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Python subprocess execution detectedtests/test_skill_eval_runner.py:24 · Python subprocess execution detectedreturn subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
CRITICAL
HTML comment carrying imperative instructions to the agentreferences/html-shell/core-structure.md:17 · HTML comment carrying imperative instructions to the agentCDN 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.
AST01
LOW
Dynamic module loadingtests/conftest.py:29 · Dynamic module loadingif importlib.util.find_spec("playwright") is None:Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_late_context_eval.py:33 · Python subprocess execution detectedresult = subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Python subprocess execution detectedtests/test_doc_sync.py:31 · Python subprocess execution detectedreturn subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_verify_release.py:12 · Python subprocess execution detectedreturn subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/verify-release.py:238 · Python subprocess execution detectedcleanup_completed = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_eval_contract.py:51 · Python subprocess execution detectedresult = subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
CRITICAL
HTML comment carrying imperative instructions to the agentreferences/html-shell/export.md:11 · HTML comment carrying imperative instructions to the agentExport (always present)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentreferences/rendering/kpi.md:52 · HTML comment carrying imperative instructions to 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.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentreferences/html-shell/summary-card.md:114 · HTML comment carrying imperative instructions to the agentSummary 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.
AST01
LOW
Dynamic module loadingtests/test_skill_eval_runner.py:19 · Dynamic module loading (importlib.loader.exec_module via provenance)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.
AST05
CRITICAL
HTML comment carrying imperative instructions to the agentreferences/rendering/kpi.md:55 · HTML comment carrying imperative instructions to the agent❌ 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.
AST01
LOW
Dynamic module loadingtests/test_skill_eval_runner.py:17 · Dynamic module loadingmodule = 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.
AST05
LOW
Dynamic module loadingtests/conftest.py:18 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(mod)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
README links to an external installerREADME.md → https://github.com/kaisersong/kai-report-creator/archive/refs/tags/v1.23.3.ziphttps://github.com/kaisersong/kai-report-creator/archive/refs/tags/v1.23.3.zipFix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈2,947 tok
2 files · 177 in bundle

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.