web-archive-scraper
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches content from external, third-party archived websites via web.archive.org. This content is processed and presented to the agent, creating a surface for indirect instructions. 1. Ingestion points: scripts/search_archive.py fetches raw HTML content via the fetch_archived_content function. 2. Boundary markers: The output is formatted with summary headers, but the extracted text content is directly provided to the agent. 3. Capability inventory: Performs network GET requests to fetch data from the Wayback Machine in scripts/search_archive.py. 4. Sanitization: The extract_text function uses regular expressions to remove HTML tags, scripts, and styles, providing some level of cleaning, though it does not prevent text-based injection patterns.
- [EXTERNAL_DOWNLOADS]: The skill requires the requests library and connects to web.archive.org. These are well-known resources necessary for the skill's stated purpose of web archiving.
Audit Metadata