skills/garethmanning/education-agent-skills/historical-thinking-strategy-modelling-guide/Gen Agent Trust Hub
historical-thinking-strategy-modelling-guide
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided document descriptions and strategy preferences, which are then processed by the AI to generate a script. This creates an indirect prompt injection surface. 1. Ingestion points: External content enters the agent context through the
document_description,target_strategies,student_level, and other input fields defined inSKILL.md. 2. Boundary markers: The instructions do not use delimiters or specific protective commands to separate user-provided text from the agent's core instructions. 3. Capability inventory: A review of the skill body confirms it does not use subprocesses, file-writing tools, or network operations. 4. Sanitization: The skill does not implement any validation, filtering, or escaping for the user-provided data before processing.
Audit Metadata