fsi-strip-profile
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- Command Execution: The skill utilizes shell commands (
sofficeandpdftoppm) to convert generated PowerPoint presentations into images. This functionality is intended to allow for visual quality assurance by the agent to detect layout issues. - Indirect Prompt Injection: The skill gathers data from external platforms like SEC filings and financial news, which introduces a surface where untrusted data could potentially influence the agent's behavior. Ingestion points: Data is retrieved from external websites and corporate filings as described in the Research section of
SKILL.md. Boundary markers: The instructions require the agent to present a research outline for user approval before generating the slides. Capability inventory: The skill utilizes shell execution and file-writing tools. Sanitization: A manual human review step is mandatory to confirm the accuracy and safety of the gathered data before the slide creation process begins.
Audit Metadata