The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted user-generated content from X timelines, which represents a significant surface for indirect prompt injection attacks.
Ingestion points: The skill uses src/timelineViewer.js and src/timelineScraper.js to collect data directly from the x.com/home timeline.
Boundary markers: No specific boundary markers or instructions to treat scraped content strictly as data are provided in the skill documentation.
Capability inventory: The skill automates timeline navigation, post collection (including text, media URLs, and author metadata), and data export to JSON.
Sanitization: There is no evidence of sanitization or filtering logic to prevent the agent from interpreting instructions embedded within the scraped tweet text.
[NO_CODE]: The implementation details for the referenced scripts (src/timelineViewer.js and src/timelineScraper.js) are not provided within the skill definition. As a result, the internal behavior of these scripts—including whether they perform unauthorized network requests or secondary data exfiltration—cannot be verified.

timeline-viewing