fin-guru-create-doc

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its document generation workflow.
  • Ingestion points: The workflow in SKILL.md requires gathering 'analysis data, recommendations, metrics' from potentially untrusted or external sources to populate templates.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the gathered data are present.
  • Capability inventory: The skill has file-write capabilities, saving generated documents to the {project-root}/fin-guru-private/ directory.
  • Sanitization: There are no instructions for sanitizing or validating the input data before it is interpolated into the final document.
  • [SAFE]: No suspicious network operations, credential exposures, or remote code execution patterns were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 09:19 PM