Back to skill
Skillv2.0.1
ClawScan security
HTML Coder · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 9, 2026, 11:40 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only HTML reference/authoring helper that asks for no credentials or installs and its content is consistent with its stated purpose.
- Guidance
- This appears to be a coherent, instruction-only HTML reference skill and does not request credentials or install software. Before installing, consider that the skill's provenance/homepage is unknown — if you need an auditable source prefer skills with known authors or hosted repos. Also review any generated HTML that pulls remote resources (CDNs, analytics) before using it in production: add SRI/integrity attributes and confirm you are comfortable including third‑party resources. Finally, always review produced code for security/accessibility details (CSP, form endpoints, input validation) before deploying.
Review Dimensions
- Purpose & Capability
- okName and description match the included SKILL.md and reference files (HTML, accessibility, forms, media, HTML5 APIs). The skill does not request unrelated credentials, binaries, or configuration.
- Instruction Scope
- okRuntime instructions are purely documentation and examples for HTML/CSS/JS authoring. They do not instruct the agent to read system files, access environment variables, or exfiltrate data. External URLs referenced are standards and common CDNs, which is expected for an HTML authoring skill.
- Install Mechanism
- okNo install spec and no code files that would be written to disk—this is an instruction-only skill, the lowest-risk install model.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. The references include example CDN links and validator sites, which are appropriate for the stated purpose. Note: the skill's source/homepage are unknown, so provenance cannot be verified.
- Persistence & Privilege
- okalways is false and the skill does not request persistent/system privileges. The default ability for the agent to invoke the skill autonomously is normal and not concerning here given the lack of privileged operations.