assignation-refere-communication-associe-selim-brihi

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (SAFE): The skill contains a standard vulnerability surface as it ingests user input via 12 structured questions to generate a legal document. This is the primary function of the skill and no malicious manipulation was detected.
  • Ingestion points: User responses to the 12 questions defined in workflow-informations.md.
  • Boundary markers: Absent; the skill does not explicitly instruct the agent to use delimiters or ignore instructions within user input.
  • Capability inventory: Writing and presenting a final document in .docx format.
  • Sanitization: Absent; the skill relies on the agent's internal safety filters for handling the content of user responses.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:47 PM