The Agent Skills Directory

[COMMAND_EXECUTION]: Uses curl and jq to interact with the Altium 365 REST API and process JSON responses.
[COMMAND_EXECUTION]: References a CLI tool named zero for diagnostic checks of connector status and environment variables.
[COMMAND_EXECUTION]: Performs file system operations by writing and reading JSON payloads (e.g., /tmp/altium365_request.json) and exporting data to the /tmp/ directory.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes untrusted data from an external API (Altium 365).
Ingestion points: Data enters the agent's context through API responses containing requirement names, descriptions, and test notes (SKILL.md).
Boundary markers: No explicit delimiters or boundary markers are defined to isolate API content from the agent's internal reasoning.
Capability inventory: The skill allows network requests via curl and file system writes to /tmp/.
Sanitization: There are no instructions for validating or sanitizing the data fetched from the API before it is utilized by the agent.
[DATA_EXFILTRATION]: Performs network operations to endpoints defined by the user-controlled ALTIUM365_WORKSPACE_URL. Authentication is appropriately managed through the ALTIUM365_TOKEN environment variable, avoiding hardcoded secrets.

altium-365