The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions and prompt templates for keyword research. It does not include any executable scripts, binary files, or configuration that grants dangerous permissions.
[PROMPT_INJECTION]: The skill has a theoretical surface for indirect prompt injection as it ingests untrusted data from user arguments and potentially from external web search results. However, there are no exploitable capabilities (such as shell execution or file system access) that could be leveraged by such an injection.
Ingestion points: User input via $ARGUMENTS and external data retrieved through the suggested web search queries in Step 2.
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external search results as untrusted content.
Capability inventory: No code-based capabilities, file-writing tools, or network operations are defined or requested in the skill.
Sanitization: No sanitization or validation of the ingested data is specified.

blog-research