The Agent Skills Directory

[COMMAND_EXECUTION]: The skill's documentation instructs the agent to construct and execute shell commands via the Bash tool that include placeholders for user-supplied data, such as file paths, brand slugs, and marketing content. This pattern creates a significant risk for command injection if the inputs are not properly sanitized or escaped before the shell command is executed.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it is designed to ingest and process untrusted external data.
Ingestion points: Marketing content files, inline text snippets, and JSON evidence files referenced in SKILL.md.
Boundary markers: None; there are no instructions to use delimiters or ignore potentially malicious instructions embedded within the marketing copy being analyzed.
Capability inventory: The skill possesses the ability to execute shell commands via the Bash tool to run its evaluation suite.
Sanitization: The instructions do not specify any sanitization, validation, or escaping of the ingested content before it is passed to the execution scripts.

check