architect
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to inspect the current repository and external registries (specifically robium-apps) to inform its architecture decisions. This creates a surface where malicious instructions embedded in project files or registries could influence the agent's behavior.
- Ingestion points: SKILL.md (Directives to 'Inspect the repository and robium-apps registry first').
- Boundary markers: No specific delimiters or warnings for embedded instructions are provided.
- Capability inventory: The skill routes implementation tasks to other specialized skills such as ros2, environments, and integration, which possess file-writing and environment configuration capabilities.
- Sanitization: No explicit sanitization of ingested content is defined.
Audit Metadata