reverse-engineering-business-logic

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data (external project source code) to generate documentation.
  • Ingestion points: The skill uses Read, Grep, and Glob tools to scan project directories and read file content (e.g., API views, models, and workflows).
  • Boundary markers: The instructions lack explicit delimiters or warnings to the agent to ignore any natural language instructions found within the code being analyzed (such as malicious comments).
  • Capability inventory: The skill has the ability to read the file system and write markdown documentation to the business_logic/ directory. It does not have network access or arbitrary shell execution capabilities enabled in its allowed-tools.
  • Sanitization: There is no mention of sanitizing or escaping the content extracted from source files before it is interpolated into the final markdown output.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 08:11 PM
Security Audit — agent-trust-hub — reverse-engineering-business-logic