codemapper
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [No Code] (SAFE): The skill consists exclusively of Markdown documentation (SKILL.md and a command reference). There are no executable scripts, configuration files, or installation routines included, eliminating the risk of direct code execution from the skill itself.
- [Indirect Prompt Injection] (SAFE): The skill's primary purpose is to ingest untrusted source code and provide it to the LLM for analysis. While this creates a surface for indirect prompt injection, it is the fundamental purpose of the tool and is handled as a safe disclosure. Evidence Chain: 1. Ingestion points: Local source code files across multiple languages (Python, JS, Rust, etc.). 2. Boundary markers: None mentioned in the command documentation. 3. Capability inventory: No code or network capabilities are present in the provided files. 4. Sanitization: No sanitization logic is documented for the output.
- [Data Exposure] (SAFE): The tool facilitates reading local files to build ASTs and summaries. This is the intended functionality of a code mapper and does not involve unauthorized access or exfiltration.
Audit Metadata