The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill fetches and extracts text from archived web pages, creating a surface where malicious instructions embedded in those pages could influence the agent's behavior.
Ingestion points: The scripts/search_archive.py script fetches raw HTML content from web.archive.org using the requests library and processes it via the extract_text function.
Boundary markers: The instructions do not define specific delimiters or "ignore" warnings to prevent the agent from obeying instructions found within the fetched content.
Capability inventory: The skill has capabilities for network access (HTTP GET via requests) and standard output, which are used to retrieve and display the archived data.
Sanitization: The extract_text function in scripts/search_archive.py performs basic sanitization by using regular expressions to strip <script>, <style>, and other HTML tags before displaying the text to the agent.
[EXTERNAL_DOWNLOADS]: The skill performs network operations to interact with the Wayback Machine's CDX API and fetch archived page snapshots.
The script scripts/search_archive.py makes HTTP GET requests to web.archive.org/cdx/search/cdx for metadata and web.archive.org/web/ for page content.
These operations target a well-known service and are necessary for the skill's primary functionality.

web-archive-scraper