fsi-strip-profile

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions include shell commands (soffice and pdftoppm) used for converting PowerPoint files to PDF and then to images. This execution is intended for the agent to perform a visual quality check (text overlap and cutoff) on the generated slides.
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks due to its data-intensive research workflow.
  • Ingestion points: Data is ingested from external sources including SEC EDGAR filings, investor presentations, and news press releases (SKILL.md, Step 2).
  • Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' instructions when processing external text content.
  • Capability inventory: The skill has the capability to execute shell commands (soffice, pdftoppm) and generate PowerPoint documents using PptxGenJS.
  • Sanitization: Absent. The skill does not describe specific filtering or sanitization steps for the data retrieved from external sources before it is placed on slides.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 01:52 AM