Skills/ClawHub/kb-web-query

kb-web-query@1.0.1

VERIFIED· install only

Publisher claims: "Answer Research KB dialogue questions with team-overview-guided web search, external citations, optional reference attachments, and no QA persistence." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher myd2002 · publishing for 153 daysInstalls 881Last detonated 2d ago
$clawhub install kb-web-query
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
second launch with the clock 45 days ahead · 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; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-11 and scored it 85/100 (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 · 2 scenarios · 0 deviations
t+CategoryObserved action
0.2sprocessscript backend runs setup only
0.2sprocessscript backend runs setup only
0.3sprocesssecond launch, clock +45 days, CI unset

Static findings

HIGH
Hidden zero-width characters detectedscripts/catalog.py:1 · Hidden zero-width characters detected — may conceal contentimport jsonFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
File type combined with upload actionscripts/query_context.py:108 · File type combined with upload action — agent may exfiltrate local data files"fetchCommand": "python3 scripts/run_task.py fetch --input <payload.json> --context <context.json> --selection <page-selection.json> --evidence-output <evidence.json>",Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionSKILL.md:59 · File type combined with upload action — agent may exfiltrate local data filespython3 scripts/run_task.py fetch --input <payload.json> --context <context.json> --selection <page-selection.json> --evidence-output <evidence.json>Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionSKILL.md:35 · File type combined with upload action — agent may exfiltrate local data filespython3 scripts/run_task.py prepare --input <payload.json> --context-output <context.json>Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Hidden zero-width characters detectedscripts/gitea_api.py:1 · Hidden zero-width characters detected — may conceal contentimport base64Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
HIGH
Hidden zero-width characters detectedscripts/text_extractors.py:1 · Hidden zero-width characters detected — may conceal contentimport xml.etree.ElementTree as ETFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07

Cost to the agent

Instructions loaded
≈1,094 tok
1 file · 14 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.