faion-project-manager

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (SAFE): The skill includes functionality for cross-tool data migration and reporting, which involves ingesting data from external APIs (Jira, GitLab, Linear). This represents a potential surface for indirect prompt injection.
  • Ingestion points: Data enters through the MigrationEngine in cross-tool-migration/README.md and the reporting script in reporting-dashboards/README.md.
  • Boundary markers: The templates do not currently define explicit boundary markers or 'ignore embedded instructions' warnings for external data fields like issue summaries or descriptions.
  • Capability inventory: The agent has access to file system modification tools (Write, Edit, TodoWrite) and network-capable tool templates.
  • Sanitization: The provided Python templates perform basic field mapping but do not include explicit sanitization logic for ingested strings. This is a common design pattern for migration tools and does not constitute a malicious finding.
  • Unverifiable Dependencies (SAFE): The documentation mentions standard industry packages like pandas and requests in its integration examples. These are used for legitimate project management automation and reporting purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:14 PM