Skills/ClawHub/ibcat

ibcat@1.0.0

VERIFIED· install only

Publisher claims: "Translate and generate bilingual side-by-side PDFs preserving original layout by extracting, translating, and rendering content with BabelDOC and LLM." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher yjkj999999 · publishing for 158 daysInstalls 519Last detonated 4d ago
$clawhub install ibcat
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

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 2026-11-10 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 · 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

HIGH
Destructive file system command detectedSKILL.md:207 · Destructive file system command detectedrm -f /root/.cache/babeldoc/cache.v1.dbFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:226 · Process kill command — agent can terminate processeskill $(lsof -ti:8899) 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionSKILL.md:45 · File type combined with upload action — agent may exfiltrate local data files| Phase 2: 翻译 / Translate | — | 将提取的文本段落分批送入 LLM 翻译，生成 translations.json / Send extracted segments to LLM in batches, generate translations.json |Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandscripts/translate_pdf.sh:157 · Process kill command — agent can terminate processeskill $PROXY_PID 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedscripts/translate_pdf.sh:84 · Destructive file system command detectedrm -f /root/.cache/babeldoc/cache.v1.dbFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedSKILL.md:126 · Destructive file system command detectedrm -f /root/.cache/babeldoc/cache.v1.dbFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionscripts/split_segments.py:7 · File type combined with upload action — agent may exfiltrate local data filespython3 split_segments.py <segments.json> <output_dir> [--batch-size 260]Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Destructive file system command detectedSKILL.md:252 · Destructive file system command detectedrm -f /root/.cache/babeldoc/cache.v1.dbFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedscripts/render_pdf.sh:54 · Destructive file system command detectedrm -f /root/.cache/babeldoc/cache.v1.dbFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:200 · Process kill command — agent can terminate processeskill $(lsof -ti:8899) 2>/dev/null; sleep 1Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedSKILL.md:133 · Destructive file system command detectedrm -f /data/user/work/segments.json /data/user/work/translations.json /data/user/work/unknown_segments.jsonFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/render_pdf.sh:58 · Process kill command — agent can terminate processeskill $(lsof -ti:$PROXY_PORT 2>/dev/null) 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/render_pdf.sh:114 · Process kill command — agent can terminate processeskill $PROXY_PID 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/translate_pdf.sh:89 · Process kill command — agent can terminate processeskill $(lsof -ti:$PROXY_PORT 2>/dev/null) 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionscripts/split_segments.py:18 · File type combined with upload action — agent may exfiltrate local data filesprint(f"Usage: python3 {sys.argv[0]} <segments.json> <output_dir> [--batch-size N]")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈3,240 tok
1 file · 11 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.