earnings-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it retrieves and analyzes data from external financial websites.
- Ingestion points: According to references/workflow.md (Step 2), the agent is instructed to fetch content from investor relations pages, SEC filings, and earnings call transcripts (e.g., from Seeking Alpha).
- Boundary markers: The skill does not provide delimiters or specific instructions to ignore potential commands embedded within the retrieved text.
- Capability inventory: SKILL.md identifies the use of Python (matplotlib, pandas, seaborn) for generating charts and a DOCX skill for creating reports.
- Sanitization: The instructions do not define any validation or sanitization mechanisms for the external data before it is processed by the agent.
Audit Metadata