benzinga-automation

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (HIGH): The skill instructs users to add an external MCP endpoint (https://rube.app/mcp). Because this domain is not within the trusted scope (TRUST-SCOPE-RULE), this is classified as a high-severity finding regarding untrusted external code sources.\n- [REMOTE_CODE_EXECUTION] (HIGH): The use of RUBE_REMOTE_WORKBENCH implies the ability to execute logic on a remote server. This capability, combined with an untrusted source, poses a significant risk of arbitrary execution.\n- [PROMPT_INJECTION] (HIGH): The skill exhibits a high-severity indirect prompt injection surface (Category 8).\n
  • Ingestion points: External financial data and toolkit schemas ingested via RUBE_SEARCH_TOOLS and Benzinga API calls in SKILL.md.\n
  • Boundary markers: Absent. There are no delimiters or instructions to ignore embedded commands in the data retrieved from Benzinga.\n
  • Capability inventory: High. The agent can use RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH to perform side-effect-heavy actions.\n
  • Sanitization: Absent. No evidence of input validation or content filtering is present in the skill definition.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 08:13 AM