The Agent Skills Directory

[DATA_EXFILTRATION]: The skill accesses sensitive directory paths in the user's home directory to read configuration and brand data.
Evidence: SKILL.md instructions load data from ~/.claude-marketing/brands/_active-brand.json and ~/.claude-marketing/brands/{slug}/profile.json.
[COMMAND_EXECUTION]: The skill executes a local Python script using an environment-defined path to manage campaign data.
Evidence: SKILL.md contains the command python "${CLAUDE_PLUGIN_ROOT}/scripts/campaign-tracker.py" --brand {slug} --action list-campaigns.
[INDIRECT_PROMPT_INJECTION]: The skill ingests brand profiles, compliance rules, and industry benchmarks which are then used to shape the agent's output and behavior.
Ingestion points: Files located at ~/.claude-marketing/brands/, skills/context-engine/compliance-rules.md, and skills/context-engine/industry-profiles.md.
Boundary markers: None identified in the instructions to separate untrusted file content from system instructions.
Capability inventory: The skill has the capability to generate campaign briefs, budget plans, and UTM-tracked URLs based on the ingested content.
Sanitization: No explicit sanitization or validation of the ingested markdown or JSON content is defined in the instructions.

campaign-orchestrator