gsd-ai-integration-phase
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from multiple sources which could contain malicious instructions.
- Ingestion points: Uses
$ARGUMENTSfor phase numbers andWebSearch/WebFetchtools to retrieve external documentation and domain research. - Boundary markers: The instructions do not define clear boundaries or 'ignore' directives for the data processed by the orchestrated sub-agents.
- Capability inventory: The skill is granted
Bash,Write, andAgenttools, providing a path for malicious instructions in the input data to potentially execute commands or modify the workspace. - Sanitization: There are no explicit validation or sanitization steps for the data retrieved during the research phases.
Audit Metadata