empathy-map
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and does not execute any code or scripts.
- [DATA_EXPOSURE]: The skill instructions specify processing user-provided research data, such as transcripts and observation notes. This is the intended primary purpose of the skill and occurs within the local session context without any indicators of external exfiltration.
- [PROMPT_INJECTION]: The skill processes external data provided by the user. While it does not use explicit delimiters to isolate this data, it lacks exploitable capabilities such as network access or shell execution, making the risk of indirect prompt injection negligible.
Audit Metadata