apply-turbo-handoffs
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from files in the
.turbo/handoff/directory which are generated by other projects. This is a potential indirect prompt injection surface where malicious instructions could be embedded in the lessons. - Ingestion points: All files within
.turbo/handoff/(Step 1). - Boundary markers: The skill includes a detailed audit process and requires user approval (Step 2) before applying any changes.
- Capability inventory: The skill uses
/create-skillfor code generation and/stage-commit-pushfor repository updates. - Sanitization: Relies on human-in-the-loop review and structured auditing logic.
- [COMMAND_EXECUTION]: The skill executes other capabilities including
/create-skill,/stage-commit-push, and/update-turboto modify the filesystem and push changes to git. These operations are within the scope of the skill's intended purpose of managing repository handoffs.
Audit Metadata