algo-seo-crawl
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements a web crawler pipeline that ingests untrusted data from external domains.
- Ingestion points: The skill performs network fetches of HTML content from seed URLs and discovered links (SKILL.md, references/distributed-crawl.md).
- Boundary markers: The instructions lack explicit delimiters or warnings to the agent to ignore instructions embedded within the processed web content (e.g., in HTML comments, meta descriptions, or page body).
- Capability inventory: The skill possesses capabilities for network access and writing to shared storage systems such as Redis, PostgreSQL, and S3 (references/distributed-crawl.md).
- Sanitization: While the skill focuses on URL normalization, it does not provide mechanisms to sanitize or filter the natural language content of crawled pages to prevent the agent from obeying embedded commands.
Audit Metadata