earnings-preview
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECREDENTIALS_UNSAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The skill instructions and reference files use placeholders like
<FMP_API_KEY>,<POLYGON_API_KEY>, and<TE_API_KEY>for API authentication. This follows security best practices by avoiding hardcoded secrets while guiding the agent on where to apply credentials. - [EXTERNAL_DOWNLOADS]: The skill is configured to interact with well-known financial data services including Financial Modeling Prep, Polygon.io, and TradingEconomics. These external references are used solely for fetching financial metrics and report schedules necessary for the skill's stated purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection.
- Ingestion points: Processes user-provided transcripts, company notes, and guidance excerpts (SKILL.md).
- Boundary markers: Not explicitly defined for user-provided text blocks.
- Capability inventory: Ability to perform network requests (curl) to financial APIs (references/providers/).
- Sanitization: No specific sanitization or filtering of input text is mentioned. The risk is assessed as safe given the focused nature of the analysis and the limited capabilities available to the skill.
Audit Metadata