The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external files and command-line arguments to generate QR code images, creating a surface for indirect instructions to enter the agent's context.
Ingestion points: Data is read from text files via the --batch argument and string data via the --data argument in scripts/qrcode_generator.py. The skill also reads image files via the --logo parameter.
Capability inventory: The script has the capability to read from and write to the local file system using the pathlib and Pillow libraries.
Boundary markers: The skill lacks explicit boundary markers or instructions to the agent to ignore potentially malicious directions embedded within the data being encoded.
Sanitization: Input data is processed and encoded into images without validation or sanitization of the content itself.

qrcode-generator