The Agent Skills Directory

[COMMAND_EXECUTION]: The skill is designed to execute the sendfox-pp-cli binary for various marketing and contact management tasks. It provides instructions for the agent to run these commands in a shell environment.
[EXTERNAL_DOWNLOADS]: The skill provides installation instructions that fetch code from external sources. It uses npx -y @mvanhorn/printing-press-library and go install github.com/mvanhorn/printing-press-library/... to download and install the CLI tool and MCP server from vendor-controlled repositories.
[DATA_EXFILTRATION]: The CLI tool supports a --deliver webhook:<url> flag, which allows the agent to POST the output of any command to an arbitrary external URL. This provides a mechanism for routing account data, contact lists, and campaign details to external endpoints.
[INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted data which could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: The skill reads data from external CSV files using the audit-csv, reconcile-csv, and import-csv commands. It also accepts feedback via stdin (feedback --stdin).
Boundary markers: The instructions do not specify any delimiter or prompt engineering to isolate the content of the processed files from the agent's instructions.
Capability inventory: The skill has access to the Bash tool, file writing capabilities (e.g., forms generate --output), and network access via the CLI's webhook delivery and feedback sending features.
Sanitization: There is no mention of input validation or sanitization for the content of the CSV files or stdin input.

pp-sendfox