The Agent Skills Directory

[SAFE]: The skill manages DataForSEO API credentials by prompting the user for input and storing them in a local .env file. It follows security best practices by applying restricted file permissions (chmod 600) to the secret file and explicitly instructing the agent not to echo or commit credentials.
[COMMAND_EXECUTION]: The skill executes local scripts (preflight.sh, serp_check.py, keyword_research.py) located within its own directory structure (~/.claude/skills/seo/). These are used to interface with the DataForSEO API and process rank checking requests.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for untrusted data as it processes and displays results from the external DataForSEO API.
Ingestion points: API responses processed by serp_check.py and keyword_research.py (SKILL.md).
Boundary markers: The output is structured into markdown tables, though specific instructions to ignore embedded commands in the API data are absent.
Capability inventory: The skill uses Bash and Write tools to execute local Python/Shell scripts and write configuration files (SKILL.md).
Sanitization: No explicit sanitization or filtering of API content is mentioned in the instructions.

seo-rankings