earnings-review
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources which could potentially contain adversarial instructions designed to influence the agent's behavior.
- Ingestion points: The skill ingests content from SEC filings, management commentary, and results from external web searches (e.g., analyst takeaways, sentiment analysis).
- Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions when processing external content.
- Capability inventory: The skill has the capability to write the final analysis to the local file system in the
reports/directory. - Sanitization: No specific sanitization or filtering logic is defined for the external data ingested.
Audit Metadata