pp-skool

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the core CLI binary and an MCP server from external repositories.
  • Fetches the @mvanhorn/printing-press-library package from npm to install the Skool CLI.
  • Downloads and installs the skool-pp-cli and skool-pp-mcp tools directly from the author's GitHub repository (github.com/mvanhorn/printing-press-library) using go install.
  • [COMMAND_EXECUTION]: The skill relies on shell command execution for all community management operations.
  • Uses bash to run skool-pp-cli commands for syncing community data, ranking posts, and managing members.
  • Supports advanced operations such as running SQL queries against a local SQLite database mirror using skool-pp-cli sql.
  • Instructions include placeholders that are interpolated into shell commands at runtime.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content, which creates a potential surface for indirect prompt injection attacks.
  • Ingestion points: Retrieves posts, member bios, comments, and course content from external Skool communities via skool-pp-cli sync and classroom export (SKILL.md).
  • Boundary markers: The instructions lack specific delimiters or warnings for the agent to ignore instructions embedded within the retrieved community data.
  • Capability inventory: The agent has the capability to execute shell commands (bash), write files to the local system (--out, shell redirection), and perform network operations (SKILL.md).
  • Sanitization: There is no evidence of filtering or sanitizing community-generated content before it is processed by the agent.
  • [DATA_EXFILTRATION]: The CLI tool includes a built-in feature to deliver command output to external network locations.
  • The --deliver webhook:<url> flag allows routing the results of any CLI command to a specified HTTP endpoint (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 12:49 AM