earnings-analysis

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a potential vulnerability surface for indirect prompt injection due to its core function of retrieving and processing data from external, untrusted web sources.\n
  • Ingestion points: The skill instructions in workflow.md direct the agent to perform web searches for the latest earnings releases, SEC 10-Q/K filings on EDGAR, and earnings call transcripts on third-party sites like Seeking Alpha.\n
  • Boundary markers: The instructions do not specify any clear boundary markers or protective prompts to prevent the agent from being influenced by malicious instructions embedded in the external financial documents it analyzes.\n
  • Capability inventory: The skill has the capability to execute Python code for chart generation using libraries like matplotlib, pandas, and seaborn, and uses an external skill to create Word documents (DOCX).\n
  • Sanitization: There is no mention of sanitization or validation of the data retrieved from external sources before it is processed by the agent or used in the report templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 10:10 AM