risk-assessment-frameworks
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill framework is designed to ingest and analyze potentially untrusted data from external sources, creating a surface for indirect prompt injection.
- Ingestion points: The risk assessment logic queries database tables containing external data, including
document_content,media_article,online_extremist_content, andmedia_interviewin SKILL.md. - Boundary markers: The provided SQL and Python logic does not demonstrate the use of delimiters or specific instructions to the underlying model to ignore embedded malicious instructions in the analyzed text.
- Capability inventory: The skill performs database read operations, calculates composite risk scores, and generates early warning alerts which may influence downstream agent behavior.
- Sanitization: There is no explicit sanitization, filtering, or escaping of the ingested text content before it is processed by the analysis logic.
Audit Metadata