Skills/ClawHub/blog-topic-research

blog-topic-research@1.1.0

CAUTION· static only

Publisher claims: "Stop writing blog posts nobody searches for. This skill builds your editorial backlog from real, verifiable user demand - never from AI vibes. It mines candi..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher automatelab · publishing for 189 daysInstalls 1,034Last detonated 2 h ago
What would fix thisWatchDispute verdict

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.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-14 and scored it 69/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. 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

MEDIUM
File type combined with upload actionSKILL.md:145 · File type combined with upload action — agent may exfiltrate local data files…age (cannibalization prep) If the user has an existing backlog file (`backlog.json`, `posts.csv`, an RSS feed of published posts, whatever), ask for the path and a way to enumerate titles. The cannibalizatio…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandSKILL.md:261 · Process kill command — agent can terminate processes- **Jaccard prefilter:** token-set overlap against existing titles; drop if >=0.6 (cheap kill on obvious dupes).Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionSKILL.md:287 · File type combined with upload action — agent may exfiltrate local data files…at doesn't exist (typically the second iteration of a for-loop reading $items[1].json with only one input item). fixes: - guard with $items[i]?.json before accessing (https://githu…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
≈8,060 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.

What would make this Verified

11 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim automatelab: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim automatelabPropose a patch to the maintainer