pp-NSE India
Warn
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: MEDIUMDATA_EXFILTRATIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs a CLI binary from the author's repositories using
npx -y @mvanhorn/printing-press-libraryandgo install github.com/mvanhorn/printing-press-library/.... These sources are vendor-controlled by the author 'mvanhorn'. - [DATA_EXFILTRATION]: The CLI tool features a
--deliver webhook:<url>flag that allows command results to be POSTed to any external URL. When combined with the tool's ability to read local user data (e.g., via the--holdings ~/holdings.csvflag), this creates a direct pathway for data exfiltration. - [DATA_EXFILTRATION]: The skill mentions a feedback mechanism that can be configured to automatically transmit local data to a remote server using the
NSE_INDIA_FEEDBACK_ENDPOINTandNSE_INDIA_FEEDBACK_AUTO_SENDenvironment variables. - [COMMAND_EXECUTION]: The skill facilitates the execution of the
nse-india-pp-clibinary with user-supplied arguments to perform market analysis and portfolio tracking. - [PROMPT_INJECTION]: The skill processes untrusted external data from the NSE India API (such as corporate announcements and filings). This represents an indirect prompt injection surface where malicious text embedded in a public filing could influence the agent's behavior when it parses the tool's output.
Audit Metadata