email-prompt-building

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection vulnerability surface.
  • Ingestion points: Data is read from multiple local files including sourcing_research.md and hypothesis_set.md.
  • Boundary markers: The instructions do not define delimiters or provide specific instructions to the agent to disregard potential instructions embedded within the ingested research content.
  • Capability inventory: The skill utilizes file system read and write capabilities within the claude-code-gtm workspace directory.
  • Sanitization: No input validation or sanitization is performed on the ingested content before it is synthesized into the output prompt template.
  • [NO_CODE]: No executable script files (e.g., Python, Node.js, or Shell) were found in the skill; it relies entirely on markdown-based instructions and templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 09:42 PM