Back to skill
Skillv1.0.0
ClawScan security
Danny_Skill · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 12, 2026, 7:35 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only content-analysis helper whose requested resources and instructions match its stated purpose and do not ask for extra credentials or risky installs.
- Guidance
- This skill is instruction-only and appears coherent for producing hot-topic analyses and content ideas. Before installing, confirm where the news items will come from (the 'agent-news-tracker' or other data source) and whether that upstream source requires credentials or could include sensitive/private content you don't want analyzed. Also verify that any agent providing the news respects source attribution and privacy. The repository lists multiple SKILL.md files (duplicates with different sizes) — likely harmless but you can request the publisher clarify why there are multiple versions. Overall risk is low.
Review Dimensions
- Purpose & Capability
- okName/description describe analyzing news for hot topics and content ideas; the SKILL.md contains only analysis rules and expected input from an 'agent-news-tracker'—no unrelated credentials, binaries, or system access are requested.
- Instruction Scope
- okRuntime instructions are limited to analyzing a provided list of news items and producing structured output (hot topics, content ideas). It does not instruct the agent to read arbitrary files, access external endpoints, or exfiltrate environment variables. It does reference input from another agent ('agent-news-tracker'), which is expected and appropriate for this skill.
- Install Mechanism
- okNo install spec and no code files — instruction-only. This is the lowest-risk install model; nothing is written to disk or downloaded by the skill itself.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. That is proportionate to a purely analytic, instruction-only skill.
- Persistence & Privilege
- okalways is false and model invocation is allowed (default). The skill does not request elevated or persistent system privileges or modifications to other skills' configs.