keyword-library
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes external keyword data which could potentially contain malicious instructions.
- Ingestion points: Keyword names and metadata fetched from
/api/v1/keywordsin SKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded content are defined in the presentation workflow.
- Capability inventory: The skill performs data retrieval and presentation, and references additional capabilities in the keyword-analysis and keyword-lists skills.
- Sanitization: There is no mention of sanitization or validation for the API-returned content before it is processed by the agent.
Audit Metadata