Test the IronClaw web UI using the Claude for Chrome browser extension.
63
75%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./skills/web-ui-test/SKILL.mdLow
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow involves installing skills from a ClawHub download URL at runtime, which can fetch outsider-authored ZIP/script contents (including SKILL.md text) into the agent context; this is an outsider source via public/community registry download.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The skill explicitly instructs installing a skill by URL which the server will download at runtime from https://wry-manatee-359.convex.site/api/v1/download?slug=markdown-viewer, and the downloaded ZIP contains SKILL.md that can define skill behavior/instructions, so remote content can directly control agent prompts.
800b781
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.