The Agent Skills Directory

[SAFE]: The skill performs legitimate educational consultation tasks including searching for university programs and matching them to a user's academic profile. No patterns of data exfiltration, credential theft, or unauthorized persistence were found.
[COMMAND_EXECUTION]: The skill executes the date command to calculate current application windows and timelines. This is a functional requirement for academic planning and does not represent a security risk.
[PROMPT_INJECTION]: The skill processes untrusted data from web search results to identify program requirements (Indirect Prompt Injection surface).
Ingestion points: External program data retrieved via the WebSearch tool.
Boundary markers: Absent.
Capability inventory: Limited to shell execution of date and the WebSearch tool.
Sanitization: Absent.
Although the surface exists, it is consistent with the primary purpose of the skill and the risk is mitigated by standard agent safety protocols.

School Selection