The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses a shell script (scripts/api.sh) to perform API calls via curl and jq. The script handles arguments safely and uses set -euo pipefail to ensure robust execution.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data from the Intervals.icu API, which could potentially contain instructions intended to influence the agent.
Ingestion points: Training data (activities, wellness, events) is fetched from the Intervals.icu API endpoints in scripts/api.sh.
Boundary markers: There are no specific instructions or delimiters provided to the agent to distinguish between data and instructions within the API responses.
Capability inventory: The skill allows reading and writing athlete data to the API and includes examples of local file redirection.
Sanitization: The script performs JSON structure validation via jq but does not sanitize text fields for potential prompt injection patterns.

intervals-icu