gitea-tea
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted content from Gitea instances, creating a surface for indirect prompt injection attacks where malicious instructions could be embedded in issues, pull requests, or notification content.
- Ingestion points: The agent reads data via
tea issues ls,tea pulls ls,tea notifications ls, andtea actions runs logs(found inSKILL.md). - Boundary markers: Absent. The instructions do not define delimiters or provide warnings to the agent to disregard instructions within the fetched data.
- Capability inventory: The skill enables network operations (Gitea API interaction), filesystem modifications (cloning repositories), and secret management (creating Actions secrets) via the
teaCLI (found inSKILL.md). - Sanitization: Absent. No specific sanitization or validation steps are prescribed for the external data before it is processed or displayed.
Audit Metadata