four-core-documents
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill reads configuration and brand metadata from application-specific paths in the user's home directory, specifically
~/.claude-marketing/brands/. This data is used locally to inform the strategic analysis. - [COMMAND_EXECUTION]: The skill executes a local Python script,
engagement-state.py, via the Bash tool to update engagement metadata and versioning information. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface because it processes untrusted data from multiple sources. Ingestion points:
part-01-client-inputs/stone-facts.json,part-02-external-research/directory, and the Part 5 Client Validation Document. Boundary markers: None are implemented to separate external content from agent instructions. Capability inventory: The agent has access toBash,Write,Edit, andReadtools. Sanitization: No sanitization or validation of the ingested external content is performed before processing.
Audit Metadata