The Agent Skills Directory

[COMMAND_EXECUTION]: The skill performs local command execution to facilitate its data-gathering and verification processes. It invokes local Python scripts ("scripts/collect_sources.py" and "scripts/collect_history.py") to scan the vault for news content. It also provides a Python snippet for the agent to execute locally to verify that all generated wikilinks are valid. Test scripts ("scripts/test_*.py") utilize subprocess.run to execute the skill's utility scripts for validation purposes; these are restricted to the local environment and the skill's own logic.- [PROMPT_INJECTION]: The skill processes untrusted data by design, as it synthesizes content from various notes in the vault (Indirect Prompt Injection surface). Ingestion points: Data is ingested from the "references/" and "investing/" folders through the "collect_sources.py" and "collect_history.py" scripts. Boundary markers: The skill does not implement explicit boundary markers or delimiters when reading the content of source notes. Capability inventory: The skill has the capability to write synthesized digests to the "news/" directory and execute local helper scripts. Sanitization: There is no explicit sanitization or filtering of the content retrieved from the source notes before it is processed by the model.

daily-news-digest