drugbank-search
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from a local SQLite database containing drug monographs and pharmacological profiles. While the data source is stated to be curated pharmaceutical data, instructions embedded in text-heavy drug descriptions could theoretically influence agent behavior.
- Ingestion points: Data returned from SQLite queries including mechanism of action and indications.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard instructions found within the data.
- Capability inventory: The skill is limited to read-only database queries.
- Sanitization: No sanitization of the retrieved database content is documented.
Audit Metadata