investment-intelligence

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses dedicated tools (primary-logic connector) provided by the author to fetch investment context. All tools and resources are aligned with the author's identity.
  • [PROMPT_INJECTION]: Analysis of the indirect prompt injection surface: 1. Ingestion points: Data is ingested from third-party sources (X/Twitter, financial articles, podcasts) via the search_content, get_content, and get_ticker_content tools. 2. Boundary markers: The skill does not use specific delimiters or markers to isolate untrusted source data. 3. Capability inventory: The skill is restricted to informational data retrieval and does not possess capabilities for file system modification, shell execution, or arbitrary network requests. 4. Sanitization: No explicit sanitization or instruction-filtering logic is present for the ingested text. The risk is assessed as safe given the primary purpose of the skill and the lack of high-risk capabilities.
  • [DATA_EXFILTRATION]: No sensitive file access patterns or hardcoded credentials were found. All network operations are confined to the intended vendor tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 09:07 PM