abd-synthesis-orchestrator
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The script
run_orchestrator.pyinvokes a sibling Python tool (build.py) and git binaries viasubprocess.runto perform workflow operations and session management. - [PROMPT_INJECTION]: The skill processes untrusted content from the workspace (Ingestion points:
strategy.md,run_orchestrator.py) and interpolates it into instruction files for the agent. It lacks boundary markers to isolate external data and does not perform sanitization (Sanitization: Absent). The agent is granted capabilities to execute commands and manipulate the filesystem (Capability inventory:subprocess.run,shutil.copytree,Path.write_text).
Audit Metadata