startup-analysis

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The README.md provides installation instructions using npx plugins add himself65/finance-skills. This references the author's own package repository and is a standard procedure for installing plugins on the supported platform.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it is designed to ingest and process untrusted data from the web to perform its analysis.
  • Ingestion points: Web search results, company websites, and user-provided URLs or documents as specified in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the retrieved data.
  • Capability inventory: The skill utilizes web search and file reading capabilities to aggregate information into a summary report.
  • Sanitization: There is no evidence of sanitization or filtering of the external content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 08:00 PM