team-polish
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill acts as an orchestrator for a development workflow, enforcing a multi-phase pipeline with required user sign-off via AskUserQuestion. It delegates riskier actions like file writing to subagents that implement their own permission protocols, reducing the direct attack surface of the orchestrator.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided text via the primary argument and propagates it to subagents with access to powerful tools.
- Ingestion points: The [feature or area to polish] argument in SKILL.md.
- Boundary markers: None; the input is passed as context without delimiters.
- Capability inventory: Subagents use Bash, Task, Write, and Edit tools.
- Sanitization: No validation or filtering is performed on the user-supplied input.
Audit Metadata