tea-create-issue
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
teaCLI tool to create issues on a Forgejo instance. - Evidence: The bash command
tea issues create --title "test issue title" --description "test issue description"is defined as the primary action inSKILL.md. - [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it is instructed to explore the codebase to gather information for issue creation.
- Ingestion points: Current codebase files accessed by the agent (referenced in
SKILL.md). - Boundary markers: Absent. There are no specific delimiters or instructions provided to the agent to treat codebase content strictly as data and ignore embedded instructions.
- Capability inventory: Command execution via the
teaCLI (SKILL.md). - Sanitization: Absent. The instructions do not specify any validation or filtering of the content retrieved from the codebase before it is used in the command line.
Audit Metadata