seo-team-the-general

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the seocli command-line tool to interact with the DataForSEO API for competitive benchmarking, traffic estimation, and backlink auditing. This execution is central to the skill's utility and utilizes a well-known service provider.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the ingestion and processing of untrusted external data.
  • Ingestion points: The skill fetches live content from competitor URLs using seocli on-page live in Step 4 and search engine results via seocli serp google in multiple steps (1, 4, and 6).
  • Boundary markers: The instructions do not specify any delimiters or safety prompts to isolate the external web content from the agent's core instruction set.
  • Capability inventory: The agent has the ability to execute system commands via seocli and perform file-write operations within the workspace/seo/ directory.
  • Sanitization: There is no evidence that content retrieved from external sites is sanitized, validated, or filtered before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 09:45 AM