Skills/ClawHub/meta-analysis-topic-selector

meta-analysis-topic-selector@1.0.1

VERIFIED· install only

Publisher claims: "Topic selection assessment and topic-report generation for meta-analyses (systematic reviews). Triggered when: you want to do a meta-analysis but don't know..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher wenhan9739 · publishing for 145 daysInstalls 689Last detonated 31 h ago
$clawhub install meta-analysis-topic-selector
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 2026-11-12 and scored it 90/100 (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
File type combined with upload actionSKILL.md:351 · File type combined with upload action — agent may exfiltrate local data files- `generate_topic_report.example.json` — full example of the input JSON; also serves as the schema doc.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:295 · File type combined with upload action — agent may exfiltrate local data filespython scripts/generate_topic_report.py input.json output.mdFix: 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:299 · File type combined with upload action — agent may exfiltrate local data filespython scripts/generate_topic_report.py input.json output.md --format htmlFix: 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 actionscripts/generate_topic_report.py:11 · File type combined with upload action — agent may exfiltrate local data filespython generate_topic_report.py input.json output.mdFix: 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:298 · File type combined with upload action — agent may exfiltrate local data filespython scripts/generate_topic_report.py input.json output.htmlFix: 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 actionscripts/generate_topic_report.py:14 · File type combined with upload action — agent may exfiltrate local data filespython generate_topic_report.py input.json output.htmlFix: 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 actionscripts/generate_topic_report.py:880 · File type combined with upload action — agent may exfiltrate local data filesusage="python generate_topic_report.py <input.json> [output] [--format md|html]",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 actionscripts/generate_topic_report.py:15 · File type combined with upload action — agent may exfiltrate local data filespython generate_topic_report.py input.json output.md --format htmlFix: 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
≈6,135 tok
1 file · 15 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.

meta-analysis-topic-selector@1.0.1 safety verdict: Verified (install only) — KillerSkills