The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the find utility with the -exec flag to perform batch operations on the filesystem via exiftool. While this is the primary functionality, it grants the agent the ability to execute commands on many files at once.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection and command injection because user-provided inputs for fields like 'Artist' and 'Copyright' are interpolated directly into shell command templates (exiftool -Artist="<artist>" ...). If a malicious user provides input containing shell metacharacters (e.g., backticks, semicolons, or pipes), they could potentially execute arbitrary code in the host environment.
Ingestion points: User inputs for 'Artist', 'Copyright', and 'Rights/Usage' collected in the 'Inputs to gather' section.
Boundary markers: None present; the skill lacks delimiters or instructions for the agent to escape or sanitize user input before command construction.
Capability inventory: The skill has access to several bash utilities (exiftool, find, ls, date, cp, mkdir) as defined in the allowed-tools frontmatter.
Sanitization: None observed; the instructions place the user input directly into double-quoted strings within a shell command string.

batch-set-copyright