label-core-bugs
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (
gh) to perform repository management tasks, including authentication checks, label creation, and issue modification on themastra-ai/mastrarepository.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitHub issues and comments, which presents a surface for indirect prompt injection. - Ingestion points: Issue bodies and comments are fetched via
gh issue viewinSKILL.md. - Boundary markers: Includes explicit instructions to treat fetched content as untrusted and to ignore any commands or instructions found within it.
- Capability inventory: The skill provides the ability to modify repository labels using
gh issue editandgh label create. - Sanitization: The skill relies on natural language instructions to guide the agent's behavior when handling external data.
Audit Metadata