programmatic-seo-spy
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, creating a potential attack surface where malicious instructions embedded in a competitor's website could influence the agent.
- Ingestion points: Competitive website sitemaps and URL structures (crawled via
site-content-cataloginSKILL.md) and full page content fetched for template quality analysis (viafetch_webpageinSKILL.md). - Boundary markers: The instructions do not specify the use of delimiters (like XML tags or triple quotes) or explicit "ignore instructions" warnings to isolate external data from the agent's core instructions.
- Capability inventory: The skill allows the agent to write detailed analysis reports to the local file system (saved to the
clients/directory) and perform network requests to several external SEO API providers. - Sanitization: The skill lacks explicit sanitization or filtering logic to neutralize potential malicious payloads within the fetched web content before it is analyzed by the language model.
- [DATA_EXFILTRATION]: The skill facilitates communication with external domain analytics providers to retrieve ranking and traffic data.
- Evidence: The skill optionally connects to well-known services including DataForSEO, SEMrush, Ahrefs, and SimilarWeb. These network operations target official service domains for their intended purpose of competitive intelligence.
Audit Metadata