roblox-liveops-roadmap
Pass
Audited by Gen Agent Trust Hub on Aug 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructions specify that the agent should read external project roadmap and instruction files. This establishes an ingestion surface for indirect prompt injection, where content within those external files could attempt to influence the agent's behavior during task sequencing or release operations.\n
- Ingestion points: SKILL.md (instructions to read project roadmap and instruction files).\n
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the provided skill content.\n
- Capability inventory: The skill utilizes tools including
roblox-to-issuesandroblox-release-operations.\n - Sanitization: No specific sanitization or validation of the external content is mentioned.
Audit Metadata