The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and validate external HTML content, which creates a potential surface for indirect prompt injection attacks where malicious instructions could be embedded in the audited data.
Ingestion points: The scripts/schema_validator.py script processes HTML from files or stdin, and instructions suggest manual inspection of website source code.
Boundary markers: The skill does not provide specific instructions or delimiters to the agent to isolate untrusted content.
Capability inventory: The skill has no dangerous capabilities such as network access, system modification, or arbitrary command execution; it is restricted to local data parsing.
Sanitization: The validator script uses standard Python libraries like HTMLParser and json to safely extract and parse structured data blocks.
[SAFE]: All instructions, reference materials, and the included Python script were thoroughly reviewed and found to be free of malicious patterns, obfuscation, or unauthorized data exfiltration attempts.

schema-markup