specialist-engineering-technical-writer
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it interpolates user input directly into the instructions for a sub-agent without using boundary markers.\n
- Ingestion points: The
{the user's question}placeholder in the sub-agent prompt withinSKILL.md.\n - Boundary markers: None present to distinguish system instructions from user-provided data.\n
- Capability inventory: The skill uses the
Agenttool to execute logic via specialized sub-agents.\n - Sanitization: No escaping, validation, or filtering is applied to the interpolated content.
Audit Metadata