public-health-analyst

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is primarily composed of text-based system prompts and domain-specific markdown references. No executable code, shell scripts, or unsafe commands are included.
  • [EXTERNAL_DOWNLOADS]: The skill references established public health resources and organizations such as the CDC (wonder.cdc.gov), the World Health Organization (WHO), and the American Public Health Association (APHA). These are well-known and trusted institutional sources.
  • [DATA_EXFILTRATION]: There are no patterns suggesting the collection or external transmission of sensitive user data. The skill does not access environment variables, private configuration files, or local credentials.
  • [PROMPT_INJECTION]: The system instructions are focused on defining a professional persona (Senior Public Health Analyst) and do not contain instructions to bypass safety filters or override agent behavior.
  • [METADATA_POISONING]: The YAML frontmatter and evaluation reports are consistent with the skill's stated purpose and contain no deceptive instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 01:57 AM