flow-sync-status
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill interacts with the
bdcommand-line tool to retrieve state and suggests executingmake validate-skillsto verify repository consistency after synchronization. These actions are standard for local development workflows and do not involve untrusted remote execution. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill reads data from
.agents/beads.jsonand markdown files within.agents/specs/to serve as the source of truth. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the content being synchronized.
- Capability inventory: The skill possesses file-writing capabilities and can invoke local shell commands (
make,bd). - Sanitization: No explicit sanitization or filtering of the ingested state data is mentioned before it is reconciled into markdown files.
Audit Metadata