Create tessl tiles with docs, rules, and skills.
97
Quality
97%
Does it follow best practices?
Impact
97%
1.97xAverage score across 5 eval scenarios
Advisory
Suggest reviewing before use
Security
1 medium severity finding. This skill can be installed but you should review these findings before use.
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.
Third-party content exposure detected (high risk: 0.90). The skill's workflows (SKILL.md and references/workflows/tile-from-source.md) explicitly instruct the agent to accept and read existing content from "repo URL" or package sources and to analyze/copy that content into tiles, meaning it ingests arbitrary public repos/packages (untrusted user-generated third-party content) that can influence subsequent decisions and tool actions.