seo-team-the-researcher
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on executing the
seoclicommand-line utility to interact with external SEO services and perform data processing tasks as evidenced by the numerous shell command examples inSKILL.mdandreference/seocli-commands.md. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied topics, domains, and competitor lists and passes them as arguments to shell commands, creating a potential surface for injection attacks.
- Ingestion points: Untrusted data enters the skill context through user requests for keyword research involving topics, domains, and competitors, as classified in
SKILL.md. - Boundary markers: No explicit delimiters or boundary markers are defined to isolate user-supplied strings within the
seoclicommand arguments. - Capability inventory: The skill uses subprocess execution to run the
seoclitool for keyword discovery, volume enrichment, difficulty assessment, and SERP mining. - Sanitization: There is no description of sanitization, escaping, or validation mechanisms for user-provided data before it is interpolated into shell commands.
Audit Metadata