delegate
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of processing external data and passing it to sub-agents.
- Ingestion points: The skill pulls in 'relevant files' and 'previous task context' to populate sub-agent prompts as seen in the Dispatch and Review Loop sections.
- Boundary markers: There are no explicit delimiters or instructions provided to sub-agents to ignore potential instructions embedded within the data context.
- Capability inventory: The skill utilizes the 'subagent' tool to perform implementation tasks, which naturally involves file system modifications and validation steps.
- Sanitization: The instructions do not define any sanitization, filtering, or validation logic for the external content before it is interpolated into sub-agent task goals.
Audit Metadata