The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the exiftool command-line utility for its core functionality. The accompanying embed.py script manages these operations using subprocess.run with several security-conscious design choices:
It constructs commands using lists rather than shell strings, which prevents shell injection vulnerabilities.
It utilizes the -- argument separator to ensure that filenames (even those starting with a hyphen) are correctly interpreted as paths rather than command flags.
It implements a robust path validation mechanism using Path.resolve() and relative_to() to prevent path traversal, ensuring the script only operates on files within the designated source directory.
[SAFE]: The skill operates entirely on local files and does not perform network requests or require credentials. Its implementation demonstrates high security awareness, and no malicious patterns such as obfuscation, persistence, or privilege escalation were detected.

photo-metadata