us-stock-analysis

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its reliance on external web data for analysis and report generation.
  • Ingestion points: The skill fetches current market data, news, and analyst ratings from external websites as specified in SKILL.md.
  • Boundary markers: The instructions do not provide delimiters or specific warnings to the agent to ignore instructions that might be embedded in the fetched web content.
  • Capability inventory: The agent uses the ingested data to formulate investment recommendations and structured reports, which could be influenced by malicious content on analyzed pages.
  • Sanitization: There is no mention of sanitizing or validating the text retrieved from external sources before it is processed by the agent.
  • [NO_CODE]: The skill consists exclusively of Markdown files and documentation. No executable scripts, binaries, or configuration files that execute code were found in the skill package.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 06:49 AM