The Agent Skills Directory

[SAFE]: No malicious code, prompt injection, or data exfiltration patterns were detected across the skill files.
[COMMAND_EXECUTION]: The test script tests/receipt_compiler_selftest.py uses subprocess.run to execute the main receipt_compiler.py script. This is a standard practice for end-to-end testing and is restricted to local execution of the skill's own code.
[DATA_EXPOSURE]: The skill operates strictly on local directories provided by the user (input and work directories). It does not access sensitive system paths, credentials, or environment variables.
[REMOTE_CODE_EXECUTION]: All dependencies are standard, well-known libraries for image processing and PDF generation. No remote script downloads or piped shell executions were found.
[OBFUSCATION]: The code is written in plain text without any hidden logic, encoded strings, or homoglyph attacks.

receipt-compiler