interactive-map-repo
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted content from external repositories, including README files, documentation, and source code (SKILL.md, Section 1). This creates a surface for indirect prompt injection if the analyzed repository contains malicious instructions. The skill includes an explicit mitigation instruction (SKILL.md, final paragraph) to treat all read content as data and not as instructions to follow or markup to copy.
- Ingestion points: Repository files including READMEs, deployment manifests (Docker, K8s), and source code files (SKILL.md).
- Boundary markers: Explicit instructional warning is present at the end of the skill.
- Capability inventory: Analysis and visualization via the interactive-map tool.
- Sanitization: Instructional prompt-based sanitization is used to prevent the agent from executing instructions found in analyzed files.
Audit Metadata