creating-experiments

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows secure patterns for handling experiment creation, delegating complex logic to other skills and using defined tool calls.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits a standard attack surface where user-supplied experiment names and hypotheses are ingested into tool parameters. 1. Ingestion points: User input for experiment metadata in SKILL.md. 2. Boundary markers: No explicit delimiters or instructions are used to isolate user-supplied strings. 3. Capability inventory: Invokes experiment-create and experiment-update tools across the creation workflow. 4. Sanitization: No sanitization or validation of user input is specified before tool invocation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 04:14 AM