multi-agent-workforce-planner
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, untrusted data to generate multi-agent workstreams.
- Ingestion points: The skill accepts 'Feature Specs' (SKILL.md) and 'Product Requirements Documents' (references/workflow-integration.md) as the primary inputs for planning.
- Capability inventory: The resulting plans direct 'Bash' agents to execute shell commands (e.g., package installation, git operations) and 'Edit' agents to perform arbitrary file modifications.
- Boundary markers: The provided templates and instructions do not include specific delimiters or instructions to ignore potential commands embedded within the requirements documents.
- Sanitization: There are no described mechanisms for sanitizing or validating the content of the external requirements before they influence the agent's planning logic.
Audit Metadata