broken-link-checker
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to crawl and analyze external web content to find broken links.
- Ingestion points: Scans user-provided URLs and crawls internal/outbound pages (SKILL.md).
- Boundary markers: The instructions do not define delimiters or provide warnings to the agent to disregard instructions found within the crawled external data.
- Capability inventory: The agent performs network requests to fetch external page content.
- Sanitization: No sanitization, escaping, or filtering of the retrieved content is described in the skill definition.
Audit Metadata