The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes curl commands to send JSON-formatted status updates to a Discord webhook during the execution of the content generation workflow.
[DATA_EXFILTRATION]: The skill transmits progress information to an external Discord webhook URL. As Discord is a well-known service and the URL is retrieved from the user's local memory or configuration, this is documented as a neutral operational feature.
[PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection because it ingests and processes content from an external catalog file (public/llms-full.txt) to guide its multi-agent generation process.
Ingestion points: Data enters the workflow via the public/llms-full.txt file located in the provided root directory.
Boundary markers: No specific delimiters or 'ignore embedded instructions' warnings are present for the ingested catalog data.
Capability inventory: The skill possesses the ability to execute workflows, write markdown files to the local drafts/ directory, and perform network operations via curl.
Sanitization: The skill includes mandatory content guardrails, such as 'not financial advice' disclaimers and prohibitions on inventing figures, which provide some output control.

finance-explainer