what-if
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions specify the execution of a local Python script,
revenue-simulator.py, to perform scenario projections. - [PROMPT_INJECTION]: The skill possesses a potential surface for indirect prompt injection by processing external data files that could contain malicious instructions.
- Ingestion points: Reads data from
~/.claude-marketing/brands/{slug}/profile.json,~/.claude-marketing/brands/{slug}/_manifest.json, and~/.claude-marketing/brands/_active-brand.json. - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are mentioned to separate ingested data from agent instructions.
- Capability inventory: The skill utilizes the
marketing-scientistagent and executes a local scriptrevenue-simulator.py. - Sanitization: The instructions do not define any sanitization, validation, or escaping logic for the content of the brand files.
Audit Metadata