copilot-flow
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a logical orchestration process for software development, leveraging trusted AI platforms and standard file-based state management without suspicious external dependencies or unauthorized network operations.- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes untrusted user requirements and existing source code files.
- Ingestion points: User-provided task descriptions through slash commands and existing codebase files read during the analysis and review phases.
- Boundary markers: The skill instructions do not define specific delimiters or explicit warnings to ignore instructions embedded within the processed data.
- Capability inventory: The agent has the ability to read and write files on the local file system and execute tools via the Copilot MCP server.
- Sanitization: No sanitization or validation logic is documented for the external data ingested into the workflow.
Audit Metadata