implement
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
gh(GitHub) andgitcommand-line interfaces to manage ticket assignments, branch creation, and code commits. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from external sources such as ticket trackers and specifications, which introduces a surface for instruction injection.
- Ingestion points: The agent is directed to read the ticket body and linked specification sections for full context before starting work.
- Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded within the ticket data.
- Capability inventory: The skill possesses shell execution capabilities (via
ghandgit) and the ability to modify the project's source code and tests. - Sanitization: There is no evidence of input validation or content filtering for data retrieved from the external tracker.
Audit Metadata