campaign-plan
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface identified through the ingestion of local brand data and configuration files.
- Ingestion points: The skill loads context from
~/.claude-marketing/brands/_active-brand.json,profile.json,_manifest.json, and agency SOPs from~/.claude-marketing/sops/. - Boundary markers: The skill does not specify delimiters or provide instructions to the agent to differentiate between its core operating logic and the brand-specific data being ingested.
- Capability inventory: The skill is restricted to marketing architecture and planning tasks; it does not have access to tools for network communication, arbitrary system command execution, or file system modification.
- Sanitization: There is no evidence of validation, filtering, or sanitization of the content retrieved from the brand profile or manifest files.
Audit Metadata