The Agent Skills Directory

[DATA_EXFILTRATION]: The skill accesses configuration and profile files located in the user's home directory.
Evidence: The process loads data from ~/.claude-marketing/brands/_active-brand.json, ~/.claude-marketing/brands/{slug}/profile.json, and ~/.claude-marketing/sops/. While functional for the skill's purpose, accessing files in the home directory constitutes a data exposure risk.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the ingestion of external data files.
Ingestion points: Data is loaded from local JSON files including profile.json and _manifest.json from the ~/.claude-marketing/ directory.
Boundary markers: None identified. The instructions do not specify the use of delimiters or warnings to ignore instructions within the ingested data.
Capability inventory: The skill performs local file read operations via the agent environment.
Sanitization: No sanitization or validation of the ingested file content is described before it is used to influence the agent's output.

influencer-brief