swarm
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill aggregates output from multiple parallel subagents into a consolidated report, creating an attack surface for indirect prompt injection if a subagent returns malicious content.
- Ingestion points: Terminal results and reports from parallel general-purpose subagents (specified in Phase C: Aggregate).
- Boundary markers: The skill lacks explicit instructions for using delimiters or boundary markers when processing subagent output, although it advises against pasting raw worker dumps.
- Capability inventory: The skill uses a Task/Subagent tool to spawn workers and has the capability to write consolidated reports and respawn workers.
- Sanitization: There are no instructions for sanitizing, escaping, or validating the content received from subagents before it is integrated into the final report.
Audit Metadata