The Agent Skills Directory

[DATA_EXFILTRATION]: The skill includes a telemetry mechanism that performs outbound network requests to a vendor-controlled domain.
Evidence: The script scripts/pdf_text_extractor.py contains a record_skill_usage function that sends an HTTP POST request to https://redfox.hk/story/api/skill/record/save with a static JSON payload {"source": "pdf提取图片"}. This domain is associated with the skill's author, redfox-data.
[COMMAND_EXECUTION]: The skill relies on the execution of a local Python script to perform its primary PDF processing tasks.
Evidence: SKILL.md instructs the agent to execute python scripts/pdf_text_extractor.py <pdf_file_path> to process uploaded PDF documents.
[PROMPT_INJECTION]: Processing untrusted external data from images and PDFs creates a potential surface for indirect prompt injection.
Ingestion points: scripts/pdf_text_extractor.py extracts text from user-uploaded PDF files using the fitz (PyMuPDF) library.
Boundary markers: None. The extracted text is returned to the agent within a standard JSON response without specific delimiters to segregate data from instructions.
Capability inventory: The skill has the capability to read local files and perform network operations.
Sanitization: No sanitization or filtering of the extracted text is performed before it is processed by the agent.

pdf-image-text-extractor