context-audit
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and YAML metadata without any associated scripts or executable binaries.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze instruction files, representing a potential attack surface. * Ingestion points: The skill reads project-specific instruction files (CLAUDE.md, AGENTS.md), repository skills, and global configuration files (~/.claude/CLAUDE.md). * Boundary markers: No explicit delimiters or boundary markers are defined to isolate analyzed content. * Capability inventory: The skill specifies an analysis-only approach and does not invoke tools for network communication or file writing. * Sanitization: No content filtering or sanitization is documented.
- [NO_CODE]: No scripts or external packages are included, removing risks associated with malicious code execution.
Audit Metadata