The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run a local Python script scripts/analyze_page.py to analyze user-provided URLs.
[EXTERNAL_DOWNLOADS]: The skill fetches external site assets including robots.txt, sitemap.xml, and llms.txt from remote domains for analysis.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing untrusted data from external websites without sanitization.
Ingestion points: External web content and metadata are ingested via the analyze_page.py script and direct fetches as described in SKILL.md.
Boundary markers: Absent. There are no instructions or delimiters provided to ensure the agent ignores malicious instructions embedded within the fetched website data.
Capability inventory: The skill possesses the ability to execute local scripts and write report files to the local filesystem.
Sanitization: Absent. No filtering or sanitization of the external content is performed before processing.

market-seo