skills/garethmanning/education-agent-skills/wellbeing-learning-connection-mapper/Gen Agent Trust Hub
wellbeing-learning-connection-mapper
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown instructions and YAML metadata meant to guide an AI's conversational response. It does not include any scripts, binaries, or automated command execution.
- [SAFE]: All external references provided in the metadata (Fredrickson, Hattie, Roffey, Durlak, Seligman) are citations to academic literature and peer-reviewed studies. There are no links to untrusted domains or external code sources.
- [PROMPT_INJECTION]: Analysis of the 'IMPORTANT' blocks and system instructions shows they are functional constraints intended to ensure the AI remains honest and evidence-based (e.g., 'Do not overstate the evidence'). These are benign instructional reinforcements rather than attempts to bypass safety guardrails.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes user-provided strings for 'wellbeing_intervention' and 'school_context', the impact is limited to text generation within a pedagogical framework. It does not grant the model access to sensitive tools or file systems that could be exploited via malicious input.
Audit Metadata