multi-agent-coordination
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill relies on reading and writing to a shared file (docs/MULTI_AGENT_COORD.md) to synchronize state between multiple agents, which serves as a potential vector for cross-agent instruction injection.
- Ingestion points: docs/MULTI_AGENT_COORD.md (Session Start Protocol).
- Boundary markers: Absent; the instructions do not specify delimiters or warnings to ignore instructions within the file.
- Capability inventory: The skill allows use of git, Read, Write, and Edit tools.
- Sanitization: Absent; there is no validation or filtering of the content read from the coordination file before the agent processes it.
Audit Metadata