to-roadmap

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external design documents and user-provided context to generate roadmap briefs.
  • Ingestion points: The agent is instructed to read referenced design or plan documents in Step 1 of SKILL.md.
  • Boundary markers: The instructions lack explicit delimiters or instructions to ignore embedded commands within the ingested text context.
  • Capability inventory: The skill performs file system writes to the docs/roadmaps/ directory and executes git commit commands as described in Step 4 and 5 of SKILL.md.
  • Sanitization: No sanitization or validation of the external content is performed before it is interpolated into the roadmap templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 07:28 AM
Security Audit — agent-trust-hub — to-roadmap