demographics-analysis
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs legitimate demographic research using official government and academic data sources as specified in its instructions. The logic is transparent and focuses on factual data gathering.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted content from the web to extract demographic data.
- Ingestion points: The skill uses the
WebFetchtool to read content from external URLs found during research (e.g., census.gov, bls.gov, etc.). - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the fetched data.
- Capability inventory: The skill utilizes
Write,Edit, andReadcapabilities to generate local report files. - Sanitization: There is no explicit sanitization or validation logic for the content retrieved from external sources before it is processed by the agent.
Audit Metadata