The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill directs the agent to download the vestaboard-pp-cli and vestaboard-pp-mcp binaries from the vendor's infrastructure at github.com/mvanhorn/printing-press-library and the @mvanhorn/printing-press-library package on the NPM registry.
[REMOTE_CODE_EXECUTION]: The skill instructions provide commands to install required tools using npx and go install, which involves fetching and executing code from external repositories to set up the execution environment.
[DATA_EXFILTRATION]: The CLI tool contains a --deliver webhook:<url> feature that enables the agent to POST command results, which may include message contents or status data, to arbitrary external URLs. Additionally, the feedback command allows for the transmission of local logs to a remote endpoint if a specific environment variable is configured.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface that could be exploited to influence agent behavior through content displayed on a physical Vestaboard.
Ingestion points: The message get and message preview commands read live layout data from the Vestaboard API into the agent's context.
Boundary markers: The instructions do not define specific delimiters or warnings to ignore embedded instructions within the message content.
Capability inventory: The skill has the ability to execute shell commands via Bash, modify board state, and update authentication tokens.
Sanitization: No sanitization or validation logic is specified for the data retrieved from the display before it is processed by the agent.

pp-vestaboard