The Agent Skills Directory

[COMMAND_EXECUTION]: Instructs the agent to execute shell-based curl commands to interact with API endpoints for job status updates.\n- [DATA_EXFILTRATION]: Performs network requests to an external service specified by the LAYERPROOF_BASE_URL environment variable. While this is a functional requirement, it involves sending an API key and interacting with a remote domain.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via the output field in the API response, which the agent is instructed to summarize.\n
Ingestion points: The output field of the JSON response from the /api/v2/jobs/{activityId} endpoint.\n
Boundary markers: Not specified; the agent lacks instructions to treat external API data as potentially untrusted or to use delimiters.\n
Capability inventory: The agent can execute curl commands and read sensitive environment variables like LAYERPROOF_API_KEY.\n
Sanitization: No sanitization or validation logic is defined to check the content of the output field before it is processed and summarized by the agent.

jobs