keyword-research
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains no executable scripts, binaries, or shell commands. It consists entirely of natural language instructions and metadata.
- [SAFE]: The skill references a local file (
../../seo/keyword-research/WORKFLOW.md) to define its operational logic. This is a standard modular design pattern and does not involve network requests or unauthorized data access. - [INDIRECT_PROMPT_INJECTION]: The skill processes instructions from a local documentation file. While this technically creates a surface where instructions are loaded from an external source, it is restricted to the local file system and follows the intended design of the agent's workflow management. Standard guardrails apply to the content of the loaded workflow.
Audit Metadata