client-onboarding

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of markdown instructions for an AI agent and does not include any scripts, binaries, or executable code.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its instruction to read and incorporate data from external files.
  • Ingestion points: The agent is directed to read brand profiles, guidelines, and templates from the ~/.claude-marketing/ directory.
  • Boundary markers: The instructions do not define any specific delimiters or 'ignore' commands for the content of the loaded files.
  • Capability inventory: The skill is limited to text generation and does not have the capability to execute system commands, access the network, or write to the filesystem.
  • Sanitization: There is no specified mechanism for validating or sanitizing the content of the brand-related files before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 01:03 PM