buildbetter
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
bbCLI tool to perform authentication checks (bb auth status), system diagnostics (bb doctor), and manage repository hooks. - [EXTERNAL_DOWNLOADS]: The skill instructions include commands to add and install plugins from the vendor's official GitHub repository (
buildbetter-app/skills). - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data such as customer feedback, support conversations, and recordings, creating a surface for potential indirect prompt injection attacks.
- Ingestion points: Support conversations, surveys, analytics context, and recordings in
SKILL.md. - Boundary markers: None provided in the skill instructions to delimit untrusted data.
- Capability inventory: Executes local CLI commands (
bb), manages git hooks, and installs plugins. - Sanitization: No specific sanitization or filtering logic is documented for the ingested feedback data.
Audit Metadata