seo-backlink-outreach
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted data from the open web.
- Ingestion points: External prospect websites and SERP data fetched via DataForSEO tools and web search functionality in Phase 3.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing external content.
- Capability inventory: The skill can read local markdown files, write new markdown files to the local system, and interact with external SEO APIs.
- Sanitization: There is no explicit sanitization or validation of the content retrieved from external websites before it is used to generate outreach templates.
- [DATA_EXFILTRATION]: The skill performs network operations to external domains to qualify prospects and perform SEO analysis.
- Network operations: Interacts with the DataForSEO API and performs generic web searches/fetches on prospect domains.
- Data access: Reads local project configuration and documentation files (e.g.,
brand-voice.md,topical-clusters.md) to personalize the outreach. - Analysis: While the skill accesses project data and performs network requests, these actions are intrinsic to its primary purpose as an SEO tool and do not show signs of malicious exfiltration.
Audit Metadata