target-intelligence-zhcn
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to connect to remote MCP servers hosted on the author's domain at
connect.patsnap.comto retrieve pharmacological, clinical, and patent data.- [COMMAND_EXECUTION]: The setup guide provides shell commands for users to run (claude mcp add) to register the necessary MCP transport endpoints for the skill to function.- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and summarize large volumes of external data from patents, scientific literature, and clinical trial results. - Ingestion points: Data is retrieved from external sources using tools such as
ls_patent_fetch,ls_paper_fetch,ls_news_fetch, andls_clinical_trial_fetchin files likeSKILL.md. - Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded formatting within the retrieved external content.
- Capability inventory: Retrieved data is analyzed and summarized into reports; there are no subprocess executions or file-system writes performed on the external content.
- Sanitization: There is no evidence of automated sanitization, filtering, or validation logic for the content fetched from external databases.
Audit Metadata