milestones
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI tool (
gh) for all repository interactions, including fetching data and making modifications. This is standard behavior for the skill's purpose. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from GitHub, which could potentially contain malicious instructions.
- Ingestion points: Data is ingested through
gh apiandgh issue listcalls inSKILL.mdandreferences/ops.md. - Boundary markers: The skill explicitly requires user approval before any mutations (editing milestones, moving issues, closing) are performed on GitHub.
- Capability inventory: The agent is authorized to modify milestones, manage issues, and trigger related release skills like
stage-itandship-it. - Sanitization: There are no explicit instructions for sanitizing or escaping content retrieved from external GitHub fields before processing.
Audit Metadata