Ops AI Analyst

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by design.
  • Ingestion points: The query input field in SKILL.md accepts arbitrary natural language text from the user.
  • Boundary markers: The instructions explicitly mandate passing the user's question "as-is" to the query engine, providing no delimiters or "ignore embedded instructions" warnings to isolate the user input from the agent's logic.
  • Capability inventory: The skill utilizes the ops_tables capability to perform ai_query_ops_table (data retrieval) and get_ops_insights (data analysis).
  • Sanitization: There is no evidence of input validation, escaping, or filtering of the user-provided query before it is processed by the AI query engine.
  • [NO_CODE]: The skill contains no scripts, binaries, or external code dependencies. It relies entirely on natural language instructions and platform-native actions (ai_query_ops_table, get_ops_insights) to perform its tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 11:37 AM