Skills/ClawHub/tencent-docs-stable

tencent-docs-stable@1.0.4

VERIFIED· install only

Publisher claims: "Stable write path for Tencent Docs (腾讯文档) when the MCP connector fails. Use when any Tencent Docs write, upload, push, or paragraph insert fails or times out, when connector init reports no_token, or when long content truncates silently. Trigger keywords: tencent docs upload failed, tdoc_init no_token, 无token, 文档推送失败, 腾讯文档写入失败, 上传失败, connector timeout, insert paragraph failed, smart document push, 腾讯文档初始化失败, 内容被截断, 文档分块. Covers failure classification, token self-check, one retry then direct JSON-RPC fallback via runtime-resolved gateway config, 16KB chunking at paragraph boundaries, and read-back verification." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher haiyangchenbj · publishing for 26 daysInstalls 615Last detonated 4d ago
$clawhub install tencent-docs-stable
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 91/100 (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
Process kill commandSKILL.md:19 · Process kill command — agent can terminate processes…lf-check sequence and a direct JSON-RPC fallback so a broken connector does not kill the task. ## Workflow 1. [Deterministic] **Classify the failure** from the…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

No other findings across 101 lines in 2 files.

Cost to the agent

Instructions loaded
≈1,102 tok
1 file · 2 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.

tencent-docs-stable@1.0.4 safety verdict: Verified (install only) — KillerSkills