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, andGlobtools 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 itsallowed-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