The Agent Skills Directory

[COMMAND_EXECUTION]: Uses bash -c to wrap curl commands. While intended to ensure environment variable persistence across pipes, this pattern increases the complexity of command execution.
[DATA_EXFILTRATION]: The skill writes job request payloads to /tmp/cronlytic_request.json. Since /tmp is often globally readable, this can expose sensitive data like webhook URLs and authorization headers to other users or processes on the system.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection from external data sources.
Ingestion points: Fetches job lists and execution logs from api.cronlytic.com (File: SKILL.md).
Boundary markers: No boundary markers or instructions to ignore embedded commands are used when processing API responses.
Capability inventory: Network operations via curl, file writing to /tmp, and command execution via bash (File: SKILL.md).
Sanitization: No sanitization or filtering is performed on the data returned by the API before it is processed or displayed by the agent.

cronlytic