The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external files (CSV, JSON, Parquet), creating a vulnerability surface where malicious instructions embedded in the data could influence agent behavior.
Ingestion points: Reads data files using pd.read_csv, pd.read_json, and pd.read_parquet as described in the execution steps (SKILL.md).
Boundary markers: Absent. The instructions do not provide delimiters or specific guidelines for the agent to ignore potential instructions embedded within the data samples.
Capability inventory: The skill has access to powerful tools including Bash, Read, Grep, and Glob (SKILL.md).
Sanitization: Absent. There are no mentions of sanitizing or escaping the content of the data files before the agent analyzes them for schema inference.

schema-discoverer