The Agent Skills Directory

[COMMAND_EXECUTION]: The skill directs the agent to run the command python campaign-tracker.py --brand {slug} --action list-campaigns. Since the campaign-tracker.py script is not provided, its safety cannot be audited.
[COMMAND_EXECUTION]: The command execution uses the {slug} variable without sanitization, which may allow for argument or command injection if the brand slug is derived from untrusted input.
[DATA_EXFILTRATION]: The instructions require reading from ~/.claude-marketing/brands/{slug}/profile.json and ~/.claude-marketing/brands/{slug}/guidelines/_manifest.json, which could expose private brand data or credentials if they reside in the user's home directory.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it loads and follows instructions from external files (profiles and guidelines) without boundary markers or sanitization.
Ingestion points: Brand profile and guideline files located in ~/.claude-marketing/.
Boundary markers: None. The skill does not instruct the agent to distinguish between trusted instructions and potentially untrusted file content.
Capability inventory: File system read access and shell command execution.
Sanitization: No validation or escaping is applied to the data retrieved from external files or to variables used in shell commands.

marketing-automation