The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze text from external clinical studies, which constitutes an indirect prompt injection surface where malicious instructions could be embedded in the source material.
Ingestion points: scripts/pdf_extractor.py extracts text from user-provided PDF files for analysis.
Boundary markers: The skill instructions do not specify the use of clear delimiters or markers to isolate the untrusted document content from the agent's instructions.
Capability inventory: The skill performs local file writing via scripts/pdf_extractor.py (writing extracted text to extracted_text.txt).
Sanitization: No sanitization or filtering is applied to the extracted text before it is presented to the agent for assessment.
[COMMAND_EXECUTION]: The skill documentation instructs the user or agent to execute shell commands for dependency installation and script execution.
Evidence: SKILL.md contains the commands pip install PyPDF2 and python scripts/pdf_extractor.py "paper.pdf".

diagnostic-study-quality-assessment-quadas-2