specialist-design-inclusive-visuals-specialist

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it interpolates untrusted user input directly into the sub-agent's prompt without delimiters or sanitization. An attacker could potentially craft a question that attempts to override the sub-agent's instructions.
  • Ingestion points: The {the user's question} variable in SKILL.md.
  • Boundary markers: Absent. The input is passed as a raw string following the prefix Answer: .
  • Capability inventory: Spawns ephemeral specialist agents via the Agent tool.
  • Sanitization: Absent.
  • [NO_CODE]: The skill consists entirely of markdown instructions and declarative configuration, with no executable scripts, binaries, or external code dependencies included.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 08:49 PM
Security Audit — agent-trust-hub — specialist-design-inclusive-visuals-specialist