The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external, untrusted sources including news feeds and SEC filing text. Ingestion points: External content retrieved via news_browse and sec_filing_read (SKILL.md). Boundary markers: None identified to separate external data from agent instructions. Capability inventory: Uses hermes cron create for persistence and command execution, alongside network data retrieval tools. Sanitization: No validation or filtering of external text content is mentioned before processing.
[EXTERNAL_DOWNLOADS]: The skill references the author's own repository github.com/LLMQuant/skills as a resource for analysis methods.
[COMMAND_EXECUTION]: The skill utilizes the hermes cron create command to schedule and persist automated monitoring tasks.

earnings-watch