The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: The scripts scripts/content_scorer.py, scripts/redirect_checker.py, and scripts/sitemap_analyzer.py all ingest content from user-provided local files or external URLs.
Boundary markers: The skill does not employ explicit delimiters or instructions to the agent to ignore embedded prompts in the analyzed data.
Capability inventory: The skill has the capability to read local files and perform network operations (GET and HEAD requests).
Sanitization: No sanitization of the processed content for prompt injection patterns is evident in the analysis scripts.
[COMMAND_EXECUTION]: The skill relies on the execution of Python scripts (content_scorer.py, redirect_checker.py, sitemap_analyzer.py) to perform its primary SEO diagnostic functions.
[DATA_EXFILTRATION]: The scripts scripts/redirect_checker.py and scripts/sitemap_analyzer.py perform network requests to arbitrary URLs. While this is the intended purpose of the skill (auditing sites), this capability could be misused to probe internal network resources (SSRF).

seo-audit