backend-engineer
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides a clear security validation checklist including parameterized queries, input validation, and protection of PII in logs.
- [COMMAND_EXECUTION]: The agent is permitted to use Bash to execute development commands such as npm lint and npm test within the specified backend scope.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. Ingestion points: Reads from backend/ and shared/types/ directories. Boundary markers: Constraints are defined in the SKILL.md scope section. Capability inventory: Tools include Bash, Write, Edit, Task, Read, Glob, and Grep. Sanitization: No explicit sanitization logic is described for processing external file content.
Audit Metadata