The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions designed to override agent behavior, bypass safety filters, or extract system prompts were detected.
[Data Exposure & Exfiltration] (SAFE): While the skill manages sensitive data labels (PII, SSN, etc.), it does not contain hardcoded credentials, API keys, or any network exfiltration logic.
[Indirect Prompt Injection] (LOW):
Ingestion points: The classify_by_content function reads data from external tables using spark.table(table).
Boundary markers: No specific boundary markers are used in the provided code snippets as they are primarily algorithmic templates.
Capability inventory: The skill uses spark.table for reading data and ALTER TABLE for writing metadata tags.
Sanitization: Untrusted content is processed using regular expression pattern matching (re.match), which is a safe way to identify sensitive data without executing it.
[Unverifiable Dependencies & Remote Code Execution] (SAFE): No external package installations or remote script executions (e.g., curl piped to bash) were found.
[Obfuscation] (SAFE): The content is provided in clear text with no evidence of encoding or hidden characters.

data-classification