skills/naimsolong/ai-software-agency/specialist-project-management-project-management-project-shepherd/Gen Agent Trust Hub
specialist-project-management-project-management-project-shepherd
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a potential for indirect prompt injection by interpolating raw user input directly into the prompt for a sub-agent.
- Ingestion points: The variable
{the_user_question}inSKILL.mdis used to pass user-provided data to theAgenttool. - Boundary markers: There are no boundary markers (e.g., XML tags or delimiters) or instructions provided to the sub-agent to ignore potential commands embedded within the user question.
- Capability inventory: The skill uses the
Agenttool to spawn sub-agents, which allows for complex task execution based on the processed input. - Sanitization: There is no evidence of input validation or sanitization before the user question is interpolated into the system prompt.
Audit Metadata