website-estimation
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection. * Ingestion points: Phases 1 and 2 of SKILL.md instruct the agent to gather data from external sources including emails (via MCP), Jira/Linear tickets, and Figma designs. * Boundary markers: There are no instructions to use delimiters or to ignore embedded commands when processing these external inputs. * Capability inventory: The agent utilizes the gathered data to generate estimation trees and rebriefing documents (Phases 2, 4, and 7). * Sanitization: No logic is provided to validate or sanitize the content of the external project documents.
Audit Metadata