earnings-competitive-review

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • Unverifiable Dependencies & Remote Code Execution (CRITICAL): The file references/mcp-setup.md instructs users to install Homebrew using the command /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)". This pattern allows for arbitrary remote code execution from a source not included in the trusted organization list.
  • Unverifiable Dependencies & Remote Code Execution (HIGH): The skill requires the execution of npx -y octagon-mcp as documented in README.md and references/mcp-setup.md. This command downloads and runs code from an unverified third-party source (OctagonAI), posing a significant supply-chain security risk.
  • Indirect Prompt Injection (MEDIUM): The workflow in SKILL.md is designed to ingest and process untrusted external data.
  • Ingestion points: Financial earnings transcripts retrieved via the Octagon MCP server.
  • Boundary markers: Absent. The prompt templates lack clear delimiters or instructions for the agent to ignore potentially malicious embedded content.
  • Capability inventory: The skill focuses on data analysis and summarization, which directly influences the agent's internal reasoning and subsequent outputs.
  • Sanitization: Absent. There is no evidence of validation or filtering of the external transcript content before processing.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 16, 2026, 03:42 AM