The Agent Skills Directory

[Indirect Prompt Injection] (LOW): The check_completeness.py script parses untrusted document content and displays extracted strings in a report, which could be used to influence the agent's behavior. \n- Ingestion points: scripts/check_completeness.py reads user-provided .tex and .txt files. \n- Boundary markers: The script does not use delimiters or warnings when presenting extracted text to the agent. \n- Capability inventory: The skill has file system access and write capabilities through scripts/generate_template.py. \n- Sanitization: No sanitization or filtering is applied to text extracted from the input documents.

treatment-plans