build-engineer
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting and analyzing external project files, which creates a surface for indirect prompt injection.
- Ingestion points: The agent is instructed to review existing build configurations, performance metrics, and dependency graphs in SKILL.md.
- Boundary markers: The instructions lack explicit markers or delimiters to help the agent distinguish between its instructions and potentially malicious data embedded in build files.
- Capability inventory: The persona implies the ability to modify build systems and implement solutions, which may include file modifications and command execution.
- Sanitization: The skill does not define methods for sanitizing or escaping content retrieved from external build artifacts.
Audit Metadata