ai-analyzer

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted health data from various JSON sources which could contain embedded instructions to influence the agent's behavior during analysis or report generation.
  • Ingestion points: data/profile.json, data/index.json, data-example/fitness-tracker.json, data-example/sleep-tracker.json, data-example/nutrition-tracker.json, data-example/mental-health-tracker.json, data/medications.json, and data/allergies.json.
  • Boundary markers: The skill lacks explicit delimiters or instructions to the agent to ignore any embedded commands within the processed data files.
  • Capability inventory: The skill has access to file system tools (Read, Write, Grep, Glob) and the ability to execute a local Python script.
  • Sanitization: No content validation or sanitization of the JSON values is mentioned in the instructions.
  • [COMMAND_EXECUTION]: The skill executes a local Python script (scripts/generate_ai_report.py) to produce HTML reports, which constitutes local command execution within the skill's environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 12:08 PM
Security Audit — agent-trust-hub — ai-analyzer