breadth-chart-analyst

Fail

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: CRITICALEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches data from https://tradermonty.github.io/market-breadth-analysis/market_breadth_data.csv, which is flagged as a malicious URL by automated scanners (URLite).
  • [REMOTE_CODE_EXECUTION]: The core data-processing script, scripts/fetch_breadth_csv.py, is identified as malware (FileRepMalware) by reputation scanners. The skill instructions mandate the execution of this script by the agent.
  • [COMMAND_EXECUTION]: The skill requires the agent to run local Python scripts (fetch_breadth_csv.py and extract_chart_right_edge.py) to process market data and chart images.
  • [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through its data ingestion pipeline.
  • Ingestion points: Untrusted CSV data is fetched from external web sources via fetch_breadth_csv.py.
  • Boundary markers: The instructions in SKILL.md do not include protective delimiters or warnings to ignore instructions that might be embedded in the external data.
  • Capability inventory: The agent has the ability to execute shell commands and write files, creating an escalation path if malicious instructions are ingested.
  • Sanitization: While numerical values are converted to floats, string fields from the CSV (such as 'trend' or 'status') are not sanitized before being processed by the model.
Recommendations
  • CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
  • AI detected serious security threats
  • Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Sep 15, 2026, 11:20 AM
Security Audit — agent-trust-hub — breadth-chart-analyst