codemap
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates entirely within the local repository environment. It computes MD5 hashes for file change detection and creates documentation scaffolds without external network dependencies or privilege escalation attempts.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection due to its core function of processing untrusted repository data.
- Ingestion points: Repository files are read and processed by
scripts/codemap.mjsduring initialization and change detection phases. - Boundary markers: No explicit markers or "ignore" instructions are added to the generated
codemap.mdfiles to prevent downstream agents from following instructions embedded in the analyzed code. - Capability inventory: The skill executes local Node.js scripts and performs recursive directory walks and file writes.
- Sanitization: Ingested file paths and content are not filtered or sanitized for malicious instructions before being used to generate mapping reports.
Audit Metadata