The Agent Skills Directory

[PROMPT_INJECTION]: The skill includes functionality to parse external documents and scrape web content, creating a vulnerability surface for indirect prompt injection.
Ingestion points: Untrusted data enters the agent context through external files processed by /augment/text-parser, web content from /augment/scrape, and search snippets from /augment/search as described in SKILL.md.
Boundary markers: The skill documentation does not mention the use of delimiters or instructions for the agent to treat external content as untrusted data.
Capability inventory: The skill instructions detail network access to the Venice AI API and local file system interaction for document uploads.
Sanitization: No evidence of input sanitization, HTML stripping, or content filtering is provided in the documentation.
[EXTERNAL_DOWNLOADS]: The skill facilitates network communication with the Venice AI service (api.venice.ai) to perform text extraction, web scraping, and search operations.

venice-augment