us-stock-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from web search results, creating a potential vector for indirect prompt injection attacks.
- Ingestion points: As described in
SKILL.md, the agent is instructed to fetch current price data, financial statements, analyst ratings, and recent news from various third-party financial websites using web search tools. - Boundary markers: The instructions do not mandate the use of delimiters or specific safety prompts to ensure that the agent ignores instructions contained within the fetched web data.
- Capability inventory: The skill is designed for data synthesis and investment report generation. The
scripts/tests/test_skill_contract.pyfile performs local file reads ofSKILL.mdand reference files for validation purposes using thePyYAMLlibrary. The skill does not possess capabilities for arbitrary command execution, unauthorized file writing, or sensitive credential access. - Sanitization: There are no mechanisms defined in the workflows to validate or sanitize external content before it is interpolated into the agent's context for analysis.
Audit Metadata