seo-ahrefs

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes data retrieved from external web sources through Ahrefs (such as referring domain anchors and Content Explorer results), which constitutes an indirect prompt injection surface.
  • Ingestion points: Web content is ingested into the agent context via commands like /seo ahrefs content <topic> and /seo ahrefs organic <url>.
  • Boundary markers: The instructions do not specify any delimiters or safety warnings to ignore instructions embedded within the external SEO data.
  • Capability inventory: The skill utilizes MCP tools to query the Ahrefs API and interacts with other SEO-related agent capabilities.
  • Sanitization: There is no indication of sanitization or filtering of the text content retrieved from external pages.
  • [COMMAND_EXECUTION]: The documentation instructs the user to run local scripts for installation (extensions/ahrefs/install.sh, install.ps1) and operational tasks (scripts/dataforseo_costs.py). These commands are standard for configuring the environment and tracking API usage costs.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 02:37 AM
Security Audit — agent-trust-hub — seo-ahrefs