Create tessl tiles with docs, rules, and skills.
76
96%
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
Low
Low-risk findings.
1 low severity finding. 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 skill's workflows (references/workflows/tile-from-source.md, tile-from-docs.md, and docs-format.md) explicitly instruct the agent to read, copy, and analyze content from source paths including repo URLs and existing public docs, so it ingests untrusted/user-generated third-party material that can change agent behavior (e.g., converting procedural pages into skills or rules).