pp-scrape-do

Warn

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the scrape-do-pp-cli tool and supporting libraries from the vendor's GitHub repository and NPM registry.
  • [REMOTE_CODE_EXECUTION]: Directs the user to install the CLI and MCP components using go install and npx, involving the download and execution of remote code from vendor sources.
  • [DATA_EXFILTRATION]: Provides a --deliver webhook:<url> feature and a feedback command capable of POSTing data to external endpoints, allowing command output to be routed to arbitrary remote servers.
  • [COMMAND_EXECUTION]: Relies on various shell commands to operate the tool, including SQL query execution via the sql command and natural language command mapping, which could be exploited if not properly sanitized.
  • [PROMPT_INJECTION]: Exhibits an indirect prompt injection surface as it processes untrusted content from web scrapes and search results. Ingestion points: scrape-do-pp-cli google and scrape-do-pp-cli scrape (SKILL.md). Capability inventory: Subprocess execution, file writing, webhook requests, and SQL execution. Boundary markers: Absent. Sanitization: Absent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 8, 2026, 08:20 PM
Security Audit — agent-trust-hub — pp-scrape-do