ibcat@1.0.2

CAUTION· static only

Publisher claims: "国际双语中文高级翻译技能,翻译并生成保留原始版式的英中双语对照PDF文档。" Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher yjkj999999 · publishing for 179 daysInstalls 541Last detonated 31 min ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

What changed since 1.0.0

vet-skills diff ibcat 1.0.0 1.0.2

In the sandbox, this version reached for nothing 1.0.0 did not. Compared from the two recorded runs, not from source.

1.0.2 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 analysed it statically (a sandbox run is pending) on 2026-11-18 and scored it 59/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Destructive file system command detected; Destructive file system command detected; Destructive file system command detected. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

HIGH
Destructive file system command detectedSKILL.md:131 · 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:231 · 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 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 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:257 · 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 actionSKILL.md:50 · 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/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 commandSKILL.md:205 · 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:138 · 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
HIGH
Destructive file system command detectedSKILL.md:212 · 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 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
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
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
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
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

Cost to the agent

Instructions loaded
≈3,258 tok
1 file · 10 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.

What would make this Verified

21 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim yjkj999999: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim yjkj999999Propose a patch to the maintainer