The Agent Skills Directory

Indirect Prompt Injection (LOW): The skill ingests untrusted external data which could contain instructions designed to influence agent behavior. Ingestion points: The analyze_csv function in example.py reads data directly via pd.read_csv. Boundary markers: No delimiters or instructions are used to separate data from the prompt context. Capability inventory: The skill is limited to statistical calculations; no network access, file-write capabilities, or shell execution were identified. Sanitization: Relies solely on pandas parsing without content validation.

data-analysis