roblox-debug
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection due to its core functionality of processing external data. \n
- Ingestion points: The skill retrieves error messages and script content from user input and local directories during Step 1 and Step 2. \n
- Boundary markers: There are no specified delimiters or instructions to treat the ingested script content as untrusted data, which could lead the model to follow instructions embedded within the code being debugged. \n
- Capability inventory: The skill is authorized to perform file system writes and interact with MCP tools in Step 5 to apply and verify fixes. \n
- Sanitization: The instructions do not define any sanitization or validation steps for content read from external files before it is used to generate new code.
Audit Metadata