skills/naimsolong/ai-software-agency/specialist-engineering-agentic-identity-trust/Gen Agent Trust Hub
specialist-engineering-agentic-identity-trust
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill defines a subagent template that ingests untrusted user data into its operational prompt, which is a common surface for indirect prompt injection.
- Ingestion points: User input is interpolated via the
{the user's question}placeholder within theAgenttool call inSKILL.md. - Boundary markers: The template does not utilize clear delimiters or specific instructions to ensure the agent distinguishes between its core directives and the provided user input.
- Capability inventory: The skill invokes the
Agenttool to spawn subagents, passing the potentially unvetted user input directly into the specialist agent's context. - Sanitization: There is no evidence of escaping, filtering, or validation of the input before it is used to construct the final prompt.
Audit Metadata