adaptive-hint-sequence-designer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided data within its prompt, which represents a surface for indirect prompt injection. However, the risk is negligible due to the absence of executable code or high-privilege tools.
- Ingestion points: Input variables like
problem_typeandcommon_sticking_pointsare interpolated into the prompt instructions. - Boundary markers: User inputs are marked with labels but lack strong structural delimiters to separate data from instructions.
- Capability inventory: The skill is limited to text generation and has no access to the file system, network, or external commands.
- Sanitization: No specific input filtering or sanitization instructions are present.\n- [NO_CODE]: The skill consists entirely of markdown instructions and does not include any scripts, executables, or package dependencies.
Audit Metadata