ae-experiment

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified in the skill instructions or reference files. The skill focuses on legitimate experiment management tasks using the ae-cli utility.
  • [INDIRECT_PROMPT_INJECTION]: The skill involves reading and processing experiment configurations which could originate from external sources. 1. Ingestion points: Experiment details are retrieved via ae-cli experiment experiment get (as described in references/query_experiment_detail.md). 2. Boundary markers: Not explicitly defined in the instructions for the ingested data. 3. Capability inventory: Command execution via ae-cli for creating and modifying experiments. 4. Sanitization: The skill mandates validation through ae-cli experiment save validate and ready-check commands to ensure payload integrity.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 07:00 AM
Security Audit — agent-trust-hub — ae-experiment