process-db-report
Pass
Audited by Gen Agent Trust Hub on Apr 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data to generate code and commands, creating an indirect prompt injection surface.
- Ingestion points: The skill is designed to "Extract data from the pasted observability report" provided in the chat context.
- Boundary markers: Absent. The instructions do not define clear delimiters or instruct the agent to ignore any embedded natural language instructions within the pasted reports.
- Capability inventory: The skill has the authority to modify source files (specifically
packages/db/src/schema.ts) and execute shell commands viabun run db:generateandbun run db:migrate. - Sanitization: Absent. There are no instructions for the agent to validate or sanitize the report content before interpolating it into the generated code snippets or action plans.
Audit Metadata