dx-roadmap
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external markdown files which could potentially contain malicious instructions meant to influence the agent's behavior during the roadmap generation process.
- Ingestion points: The skill reads
effort.md,research/*.md,frame.md,brainstorm.md, andfoundation/glossary.md(documented inSKILL.md). - Boundary markers: There are no explicit delimiters or instructions for the agent to ignore potentially embedded commands within the ingested files.
- Capability inventory: The skill has the capability to read local project files, write new roadmap files (
roadmap.md), and update the status of existing effort files. - Sanitization: No sanitization, validation, or escaping of the external file content is described before interpolation into the agent's working context.
Audit Metadata