The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The installation instructions direct users to clone the skill from https://github.com/MagicStarfishBoost/r15-shanraisshan-claude-code-best-practice-seo.git, which is an untrusted third-party repository. This introduces unverified code into the agent's local environment.
[DATA_EXFILTRATION]: The skill is designed to handle multiple sensitive credentials including AHREFS_API_KEY, SEMRUSH_API_KEY, GOOGLE_API_KEY, OPENAI_API_KEY, and SLACK_WEBHOOK_URL. Provided integration scripts like slack-notifier.py and weekly-seo-report.sh automate the transmission of audited site data and logs to external services, creating a path for potential credential or data leakage.
[COMMAND_EXECUTION]: Integration examples for WordPress and standalone scripts demonstrate the use of shell_exec (PHP) and subprocess.run (Python) to execute the skill's CLI commands. This exposes a vector for command injection if inputs are not properly sanitized.
[INDIRECT_PROMPT_INJECTION]: The core functionality of the suite involves crawling and analyzing external websites (/content-audit, /technical-seo). This untrusted data is ingested into the agent's context, making it vulnerable to embedded instructions.
Ingestion points: The crawlPages function described in the implementation logic fetches content from target URLs.
Boundary markers: There are no explicit delimiters or instructions shown to distinguish crawled content from system instructions.
Capability inventory: The skill can perform network requests, execute shell commands, and interact with the file system for logging and reporting.
Sanitization: No evidence of sanitization or filtering of external content is present in the provided snippets.

seo-content-marketing-skill-suite