The Agent Skills Directory

[DATA_EXFILTRATION]: The skill performs network requests to https://api.monologue.to using curl. This is the official API endpoint for the Monologue service and matches the author's vendor domain, representing intended functionality for a notes-reading skill.
[DATA_EXFILTRATION]: The skill contains a reference to a local filesystem path (/Users/eleanor/repos/obsidian/intellectronica/...) within the 'Source Notes' metadata section. This describes the author's development environment for documentation purposes and does not instruct the agent to access the user's local files.
[INDIRECT_PROMPT_INJECTION]: The skill fetches and processes untrusted text data (note titles, summaries, and transcripts) from an external REST API, which could potentially contain malicious instructions.
Ingestion points: External data enters the agent context via GET requests to api.monologue.to defined in SKILL.md.
Boundary markers: No delimiters or 'ignore' instructions are specified for the fetched note content.
Capability inventory: The skill has network access via curl and JSON processing capabilities via jq.
Sanitization: The skill does not implement sanitization, filtering, or validation of the text content retrieved from the API before the agent processes it.

monologue-notes-api