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 to Bash, Write, Edit, and Read tools. Sanitization: No sanitization or validation of the ingested external content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 06:03 PM
Security Audit — agent-trust-hub — four-core-documents