The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data such as URLs and CSV files during its research and content refresh workflows (Ingestion Points). It utilizes explicit boundary markers by instructing the agent to disregard any instructions embedded in fetched content (Boundary Markers). The skill has script execution capabilities for indexing (Capability Inventory), but instructions require sanitizing inputs by ignoring commands (Sanitization).
[COMMAND_EXECUTION]: The skill invokes localized Python scripts (indexpush.py and registry-events.py) within the plugin environment to handle search engine updates and claim logging. These operations are restricted to functional SEO tasks and use environment variables for authentication.
[SAFE]: No malicious obfuscation, data exfiltration, or persistence mechanisms were found. The skill's behavior and dependencies are consistent with its stated purpose of SEO writing.

content-writer