The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute multiple local Python and shell scripts for its core operations, including backlinks_auth.py for source detection, moz_api.py and bing_webmaster.py for API interaction, and install.sh for setting up extensions. These scripts are invoked through a CLI interface to perform automated analysis tasks.
[INDIRECT_PROMPT_INJECTION]: The skill features a "Verification Crawler" (verify_backlinks.py) that processes content from external URLs to verify link status. This creates an ingestion surface for potentially malicious instructions hidden in target websites.
Ingestion points: Target URLs and link data files processed by the verify_backlinks.py crawler (specified in SKILL.md).
Boundary markers: The skill instructions do not explicitly define delimiters to isolate external content from the agent's internal reasoning.
Capability inventory: The skill possesses the ability to execute various internal scripts and perform network operations via external APIs.
Sanitization: While the skill includes a "Pre-Delivery Review" to verify data accuracy and platform signals, it lacks explicit sanitization or filtering logic designed to mitigate prompt injection from crawled content.
[EXTERNAL_DOWNLOADS]: The skill retrieves SEO data from well-known services and repositories, including Moz API, Bing Webmaster, DataForSEO, and Common Crawl. It also references an installation script for managing the DataForSEO extension within its local environment.

seo-backlinks