drug-labels-search
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to execute a local bash script (
scripts/search) to perform operations. It provides a discovery command usingfindto resolve the script path within the platform's cache directory. - [INDIRECT_PROMPT_INJECTION]: The skill acts as a surface for indirect prompt injection because it retrieves and processes drug label content from an external source (
api.valyu.ai). - Ingestion points: Data enters the agent's context through the
contentfield returned by the/searchendpoint of the Valyu API. - Boundary markers: The instructions do not define specific delimiters or warning markers to help the agent distinguish between the skill's instructions and the untrusted data returned by the API.
- Capability inventory: The skill has the capability to execute shell commands (
scripts/search) and discover file paths. - Sanitization: There is no evidence of filtering or sanitization performed on the API results before they are processed by the agent.
Audit Metadata