The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill directs the agent to install the alltrails-pp-cli binary using npx or go install from external repositories managed by the vendor.
[DATA_EXFILTRATION]: The command-line tool provides a --deliver webhook:<url> feature that allows the agent to POST command results to any user-specified URL, creating a potential path for data exfiltration.
[DATA_EXFILTRATION]: The feedback command is designed to send local data to an external endpoint if the ALLTRAILS_FEEDBACK_ENDPOINT environment variable is configured.
[COMMAND_EXECUTION]: The skill relies on executing the alltrails-pp-cli binary through the system shell to perform its tasks.
[PROMPT_INJECTION]: The skill retrieves activity, trail, and profile data from AllTrails browser and mobile surfaces, which represents a surface for indirect prompt injection.
Ingestion points: Data is fetched via commands such as alltrails list, alltrails get-v3, and alltrails list-v3 from the AllTrails API.
Boundary markers: The instructions do not include specific delimiters or warnings to the agent to ignore instructions embedded within the retrieved data.
Capability inventory: The associated CLI tool possesses capabilities for filesystem writes (--deliver file:) and network requests (--deliver webhook:).
Sanitization: No evidence of data sanitization or filtering is provided for the content ingested from the external API.

pp-alltrails