The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes external investment data which constitutes an indirect prompt injection surface.
Ingestion points: Data is ingested from the Primary Logic API via multiple endpoints including /v1/content and /v1/tickers/{ticker}/content as described in SKILL.md and api-recipes.md.
Boundary markers: The skill does not define specific delimiters or explicit instructions to ignore embedded commands within the API-returned summaries or snippets.
Capability inventory: The skill's primary capability is information retrieval and formatting. It has network access to the specified vendor API but lacks high-risk capabilities like writing to the filesystem or executing arbitrary shell commands.
Sanitization: No explicit sanitization of retrieved API content is mentioned in the logic.
[EXTERNAL_DOWNLOADS]: The skill communicates with https://primarylogic--pulse-backend-external-api-app.modal.run for data retrieval. This domain is a vendor-owned resource hosted on Modal, matching the author 'primary-logic'. References and connectivity tests in the documentation are documented as safe vendor communications.
[COMMAND_EXECUTION]: Documentation files such as api-recipes.md and validation.md contain shell script examples including curl, jq, and skills-ref. These are provided as instructional recipes for developers or manual verification and are not part of the agent's autonomous runtime execution.

primary-logic-external-api