Skills
skills/coval-ai/coval-external-skills/design-persona/Gen Agent Trust Hub

design-persona

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the coval CLI to manage resources, including authentication (coval login), resource listing, and persona creation (coval personas create).
  • [PROMPT_INJECTION]: The skill incorporates external data from user arguments and agent metadata into natural language prompts for persona creation, representing an indirect prompt injection surface. (1) Ingestion points: $ARGUMENTS and agent data from coval agents get. (2) Boundary markers: Absent. (3) Capability inventory: CLI-based persona creation. (4) Sanitization: None detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 07:05 PM