integration-orchestrator
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external project inputs, including project briefs and team configurations, to generate orchestration plans and tickets. This ingestion of potentially untrusted data represents an attack surface for indirect prompt injection.\n
- Ingestion points: Required inputs in
SKILL.mdand project briefs referenced inreferences/handoff-protocols.mdwhere external content enters the agent context.\n - Boundary markers: None explicitly defined in the instructions to ensure the agent ignores instructions embedded within the data it processes.\n
- Capability inventory: Uses high-privilege MCP tools for Jira, Linear, Notion, and GitHub (
references/platform-implementation.md), and executes browser automation via Playwright MCP (references/automation-and-qa-tooling.md).\n - Sanitization: There is no requirement to sanitize or validate external inputs before they are used to drive agent actions, ticket creation, or configuration changes.
Audit Metadata