The Agent Skills Directory

[COMMAND_EXECUTION]: The skill is instructed to run a local Python script campaign-tracker.py with the command python campaign-tracker.py --brand {slug} --action list-campaigns as part of its brand context application process.
[DATA_EXFILTRATION]: The skill accesses sensitive file paths within the user's home directory to retrieve brand information, specifically reading from ~/.claude-marketing/brands/{slug}/profile.json and ~/.claude-marketing/brands/{slug}/guidelines/_manifest.json. Accessing data in hidden application directories in the home folder is considered a high-risk data exposure.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting external data from the ~/.claude-marketing/ directory. It lacks boundary markers or sanitization logic when loading these profiles and guidelines, which are then used to enforce restrictions and influence agent output. This ingest-and-execute pattern (reading profiles and then running scripts) could be exploited if the profile data is compromised.

content-engine