roblox-systems-scripter
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-defined tasks passed through the shell wrapper. This represents the standard input surface for an AI agent and is a potential vector for indirect prompt injection.
- Ingestion points: User tasks are ingested via command-line arguments or stdin in
scripts/run.sh. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined in the instruction files.
- Capability inventory: The skill uses standard agent capabilities without specific tool restrictions in the frontmatter.
- Sanitization: No explicit input sanitization or validation logic is present in the provided scripts.
Audit Metadata