The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script named campaign-tracker.py using the ${CLAUDE_PLUGIN_ROOT} path variable to retrieve historical campaign data for analysis.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from various local files, such as profile.json and _manifest.json, creating a potential vulnerability surface if these files contain malicious instructions. 1. Ingestion points: Data is loaded from JSON and markdown files within the ~/.claude-marketing/ directory. 2. Boundary markers: The skill does not define specific delimiters to isolate external data from its own instructions. 3. Capability inventory: The skill has the capability to execute Python scripts and perform file system reads. 4. Sanitization: There is no evidence of content sanitization or validation for the data ingested from brand profiles or templates.

retargeting-strategy