marketing-referral

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface.
  • Ingestion points: The workflows for 'Existing Local Codebase' (Context B) and 'Live Website URL' (Context C) instruct the agent to process data from external, untrusted sources.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the SKILL.md to protect against malicious instructions in the audited content.
  • Capability inventory: The skill instructions include generating and writing multiple markdown documents to the local file system under the ./brands/ directory.
  • Sanitization: There are no instructions for the agent to validate or sanitize content before it is processed and used to generate outputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 04:01 AM