krt-roadmap-cartographer
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize content from various repository files, such as PRDs, schemas, and product documentation. This creates a surface for indirect prompt injection if an attacker can commit malicious instructions to those scanned files.
- Ingestion points:
SKILL.mdspecifies scanning multiple repository files includingAGENTS.md,README.md,docs/, and PRDs. - Boundary markers: The instructions do not explicitly define strict delimiters for the interpolated content from source files, although it uses a 'Source Inventory' to track contributions.
- Capability inventory: The skill is capable of writing new markdown files to the local file system (e.g.,
docs/roadmaps/ordocs/orchestration/). It does not appear to have network or shell execution capabilities. - Sanitization: No explicit sanitization or filtering of external content is described in the workflow.
Audit Metadata