review-roadmap

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze a user-provided file (roadmap path), which serves as an entry point for untrusted data into the agent's context.
  • Ingestion points: The [roadmap file path] argument specified in the frontmatter and used throughout the instructions.
  • Boundary markers: The instructions lack explicit delimiters or warnings to the subagents to ignore or treat instructions within the roadmap file as data rather than commands.
  • Capability inventory: The skill dispatches three subagents and utilizes a /research tool to perform external lookups based on the file content.
  • Sanitization: There is no evidence of sanitization, validation, or filtering of the content read from the roadmap file before it is passed to the subagents.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 07:05 AM
Security Audit — agent-trust-hub — review-roadmap