The Agent Skills Directory

[SAFE]: No malicious patterns, command injections, or exfiltration attempts were detected. The skill uses standard ServiceNow APIs and MCP tools for its stated purpose of HR data management.
[PROMPT_INJECTION]: The skill exhibits an inherent surface for indirect prompt injection because it processes unstructured text provided by interviewers.
Ingestion points: The agent reads untrusted content from the u_notes, u_strengths, and u_concerns fields in the u_interview_feedback table.
Boundary markers: The instructions do not define specific delimiters or "ignore" warnings to prevent the agent from following instructions potentially embedded within interview notes.
Capability inventory: The skill possesses capabilities to read from and update ServiceNow records via SN-Query-Table, SN-Update-Record, and SN-Create-Record (SKILL.md).
Sanitization: There is no evidence of automated sanitization or filtering of the feedback content before it is processed by the model.

interview-relevance