drug-labels-search
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local shell scripts (
scripts/search) and uses thefindcommand to resolve script paths within the agent's plugin cache directory (~/.claude/plugins/cache). - [DATA_EXFILTRATION]: The skill communicates with the
api.valyu.aiendpoint to perform searches and includes a configuration flow to collect and store a user-provided Valyu API key. - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it retrieves and displays content (drug labels, warnings, indications) from an external API.
- Ingestion points: Data returned from search queries at
api.valyu.ai/v1/search. - Boundary markers: Not present; the skill instructions do not specify delimiters to separate untrusted API content from the agent's instructions.
- Capability inventory: The skill allows the execution of local shell scripts for searching.
- Sanitization: The skill does not describe any specific sanitization or filtering of the external API content.
Audit Metadata