krea2-identity-edit

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists of instructional documentation for local image editing workflows.
  • [DATA_EXFILTRATION]: The skill explicitly instructs the agent to perform operations locally, ensuring data remains on the host machine.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied images and prompts, creating a surface for potential injection. Ingestion points: User images and prompts (SKILL.md). Boundary markers: Present in the 'Boundaries' section (SKILL.md). Capability inventory: Local workflow execution (SKILL.md). Sanitization: Agent-based refusal logic (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 03:37 AM
Security Audit — agent-trust-hub — krea2-identity-edit