Skills/ClawHub/leafather-report-audit

leafather-report-audit@3.6.1

VERIFIED· install only

Publisher claims: "数鉴-报告审计技能。做报告时就用:算数即记账,交付前对账。两条路产同一本账本——①有指标定义(ledger.yaml + indicators.yaml)→ rla_ledger 生成账本,模板里写 [[id]] 渲染,数字天生带出处、数据变了拒绝渲染;②有脚本跑数 → rla_report 录像自动记账。审计时把报告数字逐个追溯回账本,追不到即拦;覆盖率不足不许判定通过。适用三时机:出报告(算数记账)、改报告(改完拿现有账本重核,防只改一份漏其余)、查问题(数字对不上、客户质疑出处)。触发词:出数据报告、做报告、改报告、更新数据、数据补录、口径调整、重新生成报告、交付前检查、数字对不上、可追溯、审计报告。项目里已有 ledger.yaml / indicators.yaml 时,改动报告前后都应复核。产出四件套:audit.md 结论、audit.html 审计凭证、evidence.csv 证据清单、manifest.json 机检回执。不适用:改的是纯文字(不含数字)、或报告里没有需要追溯的指标。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher wopy112-gao · publishing for 0 daysInstalls 34Last detonated 25 min ago
$clawhub install leafather-report-audit
WatchReport an issue

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

What changed since 3.6.0

vet-skills diff leafather-report-audit 3.6.0 3.6.1

In the sandbox, this version reached for nothing 3.6.0 did not. Compared from the two recorded runs, not from source.

3.6.0 was not run in the sandbox (static only); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

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 2026-11-16 and scored it 88/100 (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 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedscripts/rla_audit.py:192 · Python subprocess execution detectedp = subprocess.run([sys.executable, gw, "--sql", sql, "--out", out, "--limit", "10", "--timeout", "120"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/rla_collect.py:144 · Python subprocess execution detectedp = subprocess.run(self.argv, input=str(sql), capture_output=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/rla_collect.py:163 · Python subprocess execution detectedp = subprocess.run([sys.executable, self.script, "--sql", str(sql),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/rla_selftest.py:144 · Python subprocess execution detectedreturn subprocess.run(cmd, capture_output=True, text=True).returncodeFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/rla_track.py:193 · Python subprocess execution detectedproc = subprocess.run(cmd, env=env)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/rla_selftest.py:163 · Python subprocess execution detectedr = subprocess.run(cmd, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/rla_replay.py:42 · Python subprocess execution detectedp = subprocess.run(cmd, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionscripts/rla_collect.py:13 · File type combined with upload action — agent may exfiltrate local data filespython3 scripts/rla_collect.py --trace run.trace.jsonl --ledger l.json --no-recomputeFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedscripts/rla_track.py:220 · Python subprocess execution detectedr = subprocess.run([sys.executable, str(collect),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/rla_report.py:41 · Python subprocess execution detectedr = subprocess.run([sys.executable] + args)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈2,570 tok
1 file · 30 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.

leafather-report-audit@3.6.1 safety verdict: Verified (install only) — KillerSkills