context-map
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional text for documentation organization. It does not perform any automated actions, network requests, or access sensitive local files.
- [NO_CODE]: The repository contains only a markdown instruction file. There are no scripts, binaries, or configuration files that initiate code execution.
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest external source documents to create maps, which is a potential surface for indirect injection. 1. Ingestion points: Step 1 in SKILL.md instructs the agent to read and analyze external project sources. 2. Boundary markers: No delimiters or protective instructions are used to wrap external content. 3. Capability inventory: No file system writing, network access, or shell command capabilities are defined within SKILL.md. 4. Sanitization: No sanitization of source content is described. The absence of dangerous capabilities ensures that this injection surface remains low-risk.
Audit Metadata