team-live-ops
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting untrusted data and passing it to agents with powerful capabilities.
- Ingestion points: The skill accepts user-supplied input via the
[season name or event description]argument and reads content from external files such asdesign/live-ops/economy-rules.mdanddesign/live-ops/ethics-policy.md. - Boundary markers: There are no explicit delimiters or 'ignore embedded instructions' warnings defined when passing this external content to the sub-agents.
- Capability inventory: The orchestrator and its sub-agents have access to high-privilege tools including
Bash,Write,Edit, andTask(which can spawn further processes). - Sanitization: The skill lacks explicit sanitization or validation logic for the content read from design files before it is interpolated into the prompts for the specialized sub-agents.
Audit Metadata