unity-debug
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill defines a workflow that ingest Unity console logs through the
u console getcommand. This creates a potential surface for indirect prompt injection, as malicious strings logged by an application could be interpreted as instructions by the agent. - Ingestion points: Data entering the agent context via
u console get(referenced in SKILL.md). - Boundary markers: The skill does not provide delimiters or specific instructions to the agent to treat console output as untrusted data.
- Capability inventory: The agent has the capability to modify the Unity environment using commands like
u component add. - Sanitization: There is no evidence of filtering or validation of console log content before it is presented to the agent.
Audit Metadata