Back to skill
Skillv1.0.0
ClawScan security
Content Ideas Generator · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 23, 2026, 3:48 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only brainstorming skill that asks for no credentials, installs nothing, and its runtime instructions are limited to generating content ideas—everything is consistent with its description.
- Guidance
- This skill is instruction-only and appears safe: it won’t install software or request credentials. Be mindful when using it not to paste sensitive client data or secrets into prompts. The SKILL.md mentions a paid "Content Creator Suite" upsell — verify the vendor and do not submit payment or credential information unless you trust the upgrade path. If you later enable this skill in an agent that also has skills with network or credential access, consider that combined capabilities could expose prompts to other components; restrict scope or review permissions if that is a concern.
Review Dimensions
- Purpose & Capability
- okThe name/description (content brainstorming) matches the SKILL.md examples and prompts. There are no unexpected requirements (no env vars, no binaries) that would be unrelated to generating content ideas.
- Instruction Scope
- okSKILL.md contains only prompt templates, example outputs, and an upgrade upsell. It does not instruct the agent to read files, access environment variables, call external endpoints, or collect unrelated system data.
- Install Mechanism
- okNo install spec and no code files — the skill is instruction-only, so nothing is written to disk or downloaded. This is the lowest-risk install mechanism.
- Credentials
- okThe skill requires no environment variables, credentials, or config paths. There are no requests for secrets or unrelated service tokens, which is proportionate for a brainstorming tool.
- Persistence & Privilege
- okalways is false and model invocation is allowed (default). The skill does not request elevated or persistent privileges and does not modify other skills or system configuration.