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-librarypackage from npm to install the Skool CLI. - Downloads and installs the
skool-pp-cliandskool-pp-mcptools directly from the author's GitHub repository (github.com/mvanhorn/printing-press-library) usinggo install. - [COMMAND_EXECUTION]: The skill relies on shell command execution for all community management operations.
- Uses
bashto runskool-pp-clicommands 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 syncandclassroom 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