agentic-workflow-orchestration
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The orchestration patterns described in the skill involve ingesting untrusted data from GitHub repositories, which could contain malicious instructions.
- Ingestion points: Workflows like
issue-analyzer.mdandissue-router.mdread issue titles, bodies, labels, and comments from the repository. - Boundary markers: The provided examples do not demonstrate the use of delimiters or explicit instructions for the agent to ignore instructions embedded within the processed data.
- Capability inventory: The orchestrator and workers possess capabilities to create issues, post comments, dispatch further workflows, and create pull requests via the
githubtool. - Sanitization: The skill does not explicitly implement or document sanitization or escaping mechanisms for external content before it is processed by the agents.
Audit Metadata