implementation-intention-designer
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a purely instructional framework for an AI agent. It does not include any scripts, binary files, or commands that interact with the host system or external networks.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided data such as student profiles and target behaviors. While this creates a theoretical surface for indirect prompt injection, the risk is negligible as the skill lacks any capabilities (such as file writing, command execution, or network access) that could be exploited via injection.
- [PROMPT_INJECTION]: The prompt uses role-playing and instructional emphasis (e.g., "IMPORTANT"), but these are used legitimately to guide the AI's output quality rather than to bypass safety guardrails or extract system information.
- [EXTERNAL_DOWNLOADS]: No external resources or packages are downloaded. The references cited in the metadata are for academic attribution only.
Audit Metadata