Back to skill
Skillv1.0.1

ClawScan security

Hacker news on topic AI and agent only · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignApr 1, 2026, 12:27 PM
Verdict
benign
Confidence
high
Model
gpt-5-mini
Summary
The skill's code and instructions match its stated purpose (fetching Hacker News stories about AI via the Algolia HN API); it does not request credentials or access unrelated resources.
Guidance
This skill is coherent with its description: it fetches HN stories via the Algolia API and reformats them. Before installing, note two practical points: (1) the script requires Python and the 'requests' package — the skill provides no install steps, so ensure your environment has that dependency; (2) the skill will make outbound network requests to https://hn.algolia.com — if you have network restrictions or logging requirements, confirm this is acceptable. As with any third-party code, only install if you trust the source; the included script is short and readable, but running code from unknown publishers always carries operational risk.

Review Dimensions

Purpose & Capability
okName/description promise (HN stories about AI/agents/Claude) matches the implementation: a Python script that queries the HN Algolia search API for stories containing the specified keywords.
Instruction Scope
okSKILL.md instructs running the included script and reformatting output. The script only performs an HTTPS GET to hn.algolia.com and prints results; it does not read local files, environment variables, or send data to other endpoints.
Install Mechanism
noteThere is no install spec (lowest risk). However, the included Python script depends on the third-party 'requests' library but the skill does not declare or install that dependency — operational mismatch (not a security red flag but a runtime/packaging issue).
Credentials
okThe skill requires no environment variables, credentials, or config paths. Nothing requested appears disproportionate to fetching HN stories.
Persistence & Privilege
okSkill is not always-enabled and does not request persistent privileges or modify other skills/config; autonomous invocation is allowed but is the platform default and not combined with other red flags.