setup-help
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external information such as repository documentation and user-provided outlines to generate its checklist, which introduces a surface for indirect prompt injection.
- Ingestion points: Instructions specify building a checklist from the user's outline, repository documentation, and current screen content.
- Boundary markers: There are no specific delimiters or instructions defined to isolate the external content from the agent's core operational logic.
- Capability inventory: The skill limitations acknowledge that the agent may have capabilities for command execution, remote access, and file modification, which could be targeted by an injection attack.
- Sanitization: The skill does not provide instructions for sanitizing or validating content retrieved from external sources before processing it.
Audit Metadata