The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill instructs the agent to install external software using npx -y @mvanhorn/printing-press-library and go install github.com/mvanhorn/printing-press-library/..., which involves downloading and executing code from remote sources.
[DATA_EXFILTRATION]: The intercom-pp-cli tool includes a --deliver webhook:<url> feature. This allows the output of any command—including potentially sensitive information like contact lists, admin logs, or conversation contents—to be sent to an arbitrary external URL via a POST request.
[COMMAND_EXECUTION]: User-supplied arguments are passed directly to the intercom-pp-cli binary. This could lead to command injection if the arguments are not correctly sanitized by the agent or the binary itself.
[PROMPT_INJECTION]: The skill is designed to process external content from Intercom (conversations, articles), which introduces a risk of indirect prompt injection where malicious instructions embedded in the data could influence the agent's actions.
Ingestion points: Data is pulled from Intercom conversations, articles, and contacts via various CLI commands.
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands in the data being processed.
Capability inventory: The skill can execute shell commands, perform network operations via webhooks, and write data to the local filesystem.
Sanitization: There is no explicit mechanism described for sanitizing or filtering the content retrieved from Intercom before the agent processes it.

pp-intercom