process-db-report
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to parse untrusted external data in the form of pasted database observability reports, providing an attack surface for instructions to be embedded in the input.
- Ingestion points: The skill instructions specify 'Parse report' from a 'pasted observability report' in SKILL.md.
- Boundary markers: The skill lacks explicit instructions for the agent to use delimiters or ignore instructions that may be embedded within the report data.
- Capability inventory: The skill permits the agent to modify project source code (packages/db/src/schema.ts) and provides specific shell commands for execution (bun run db:generate, bun run db:migrate).
- Sanitization: There are no instructions for validating, filtering, or sanitizing the input data before it is processed.
- [COMMAND_EXECUTION]: The skill includes shell commands for generating and applying database migrations in its action plan template. While functional, these represent a capability that could be targeted by an injection attack.
Audit Metadata