content-plan
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources which constitutes a theoretical attack surface for indirect prompt injection.
- Ingestion points: Reads sitemaps, CMS exports, Search Console data, and SERP tool outputs to identify content gaps.
- Boundary markers: The instructions do not define specific delimiters to isolate external data from internal logic.
- Capability inventory: The skill has limited capabilities, primarily focused on reading project files and writing a content plan to
.agents/content-plan.md. It does not execute arbitrary code or perform unauthorized network exfiltration. - Sanitization: No specific sanitization of external metadata or query data is described before processing.
Audit Metadata