tessl-labs/tile-creator
Create tessl tiles with docs, rules, and skills.
96
94%
Does it follow best practices?
Impact
99%
2.35xAverage score across 5 eval scenarios
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
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.
Why it was flagged
The skill's workflows (see references/workflows/tile-from-source.md and SKILL.md) explicitly accept a "source path" that can be a repo URL or package name and instruct the agent to read, analyze, and copy content from that external repo/package, meaning untrusted user-generated third-party content is ingested and used to drive tooling and decisions.
Where we found it
user-provided repository/package source (repo URL, package name, or codebase)
content-type · 8 sites
The plugin's tile-from-source workflow explicitly instructs the agent to accept a user-provided source path (repo URL, package name, or local folder), read and deeply analyze its content (code, metadata, markdown), and copy it into the tile structure — ingesting potentially untrusted third-party content that could contain adversarial prompt-injection payloads.
- Audited
- Security analysis