skills/naimsolong/ai-software-agency/specialist-design-inclusive-visuals-specialist/Gen Agent Trust Hub
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 inSKILL.md. - Boundary markers: Absent. The input is passed as a raw string following the prefix
Answer:. - Capability inventory: Spawns ephemeral specialist agents via the
Agenttool. - 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