30x-seo-backlinks
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill performs network operations using
curltoapi.dataforseo.comto fetch SEO metrics. It reads authentication credentials from a local file at~/.config/dataforseo/authto authorize these requests. This behavior is consistent with the skill's stated purpose of backlink analysis. - [INDIRECT_PROMPT_INJECTION]: The skill processes data retrieved from the DataForSEO API to generate SEO reports, which creates a potential surface for indirect prompt injection if the external source content contains malicious instructions.
- Ingestion points: Backlink profiles, anchor texts, and domain metadata retrieved from
api.dataforseo.com(SKILL.md). - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" warnings for the processed API data.
- Capability inventory: Includes
Bashfor network requests andReadfor local configuration access (SKILL.md). - Sanitization: There is no mention of explicit sanitization or validation of the API response data before it is processed by the agent.
Audit Metadata