era-alpha
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and process untrusted external data (financial reports, high-frequency industry data, and user-provided arguments) to generate investment reports.
- Ingestion points: The skill uses
$ARGUMENTS(user input) and directs the agent to 'network for latest financials and high-frequency data' (SKILL.md). - Boundary markers: There are no explicit delimiters or instructions for the agent to treat ingested data as untrusted content in the prompt templates.
- Capability inventory: The agent is authorized to use shell commands (e.g.,
date,python3 tools/financial_rigor.py) and web search tools to perform its tasks. - Sanitization: No sanitization, filtering, or validation logic is specified for the external data before it is incorporated into the agent's context.
Audit Metadata