fsi-strip-profile

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes soffice and pdftoppm via shell to convert PowerPoint files into images. This process is used for visual verification of slide layouts to identify text collisions or formatting errors.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external financial sources, creating a potential surface for indirect prompt injection where malicious instructions could be embedded in the processed data.
  • Ingestion points: Company filings (BamSEC, SEC EDGAR), investor presentations, corporate websites, Bloomberg, FactSet, and news articles (SKILL.md).
  • Boundary markers: The workflow includes multiple user confirmation steps and visual slide reviews which act as manual verification boundaries before proceeding.
  • Capability inventory: The agent can generate .pptx files and execute file conversion commands (soffice, pdftoppm).
  • Sanitization: No specific content sanitization or escaping mechanisms for the ingested external data are described in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 05:58 AM