The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install a CLI tool using npx -y @mvanhorn/printing-press-library and go install github.com/mvanhorn/printing-press-library/.... These resources are hosted on well-known platforms (npm, GitHub) and originate from the author's own repositories.
[COMMAND_EXECUTION]: The skill executes a local binary gohighlevel-pp-cli and various shell commands to perform CRM operations. It requires the Bash tool to function.
[DATA_EXFILTRATION]: The tool includes a --deliver webhook:<url> feature that allows the output of any command to be sent to an arbitrary external URL via a POST request. Additionally, the feedback command can be configured to transmit data to a remote endpoint via the GOHIGHLEVEL_FEEDBACK_ENDPOINT environment variable.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8):
Ingestion points: The agent processes untrusted data fetched from GoHighLevel, including contact details, emails, SMS messages, and conversation threads in the convo thread and contacts search commands.
Boundary markers: None. The skill does not define delimiters or provide instructions to the agent to treat the ingested CRM content as untrusted data.
Capability inventory: The skill can execute shell commands, read/write local files (--deliver file:<path>), and perform network operations (GHL API, webhooks).
Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the CRM before it is presented to the agent's context.

pp-gohighlevel