create-handoff
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to determine session names and navigate directory structures (
ls,head,xargs,git rev-parse). - [COMMAND_EXECUTION]: The skill executes a project-local Python script (
scripts/core/artifact_mark.py) viauv run. This script is used to mark the outcome of the session in a database. - [COMMAND_EXECUTION]: User-provided input from the
AskUserQuestiontool is interpolated directly into a shell command line (--outcome <USER_CHOICE>). While the instructions constrain the agent to specific options, this pattern creates a surface for indirect prompt injection or command injection if the input is not strictly validated against the expected enum values.
Audit Metadata