The Agent Skills Directory

SAFE (SAFE): No malicious patterns or security risks were detected in the skill's code or metadata.
Indirect Prompt Injection (LOW): The skill processes untrusted text data from user input and external CSV files. While it lacks explicit sanitization or boundary markers, the risk is negligible because the skill does not possess any exploitable capabilities like network access or command execution.
Ingestion points: CLI argument --text and CSV file contents via pd.read_csv in language_detector.py.
Boundary markers: Absent.
Capability inventory: None. No network requests, shell execution, or dynamic code evaluation.
Sanitization: Absent.

language-detector