gtm-channels-plan
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional content and does not include any executable scripts, shell commands, or unexpected network operations. Its behavior is entirely consistent with its stated purpose of Go-To-Market (GTM) planning.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it processes data from potentially untrusted external sources.
- Ingestion points: The skill reads business stage, persona, and journey data from Notion (steps 02-10) and retrieves community and group information through the
WebSearchtool. - Boundary markers: There are no explicit delimiters or specific instructions to the agent to disregard commands embedded within the ingested data.
- Capability inventory: The skill is capable of reading internal reference markdown files, executing research tools (
WebSearch,niche-data-finder), and writing content back to Notion. - Sanitization: The instructions do not specify any sanitization, filtering, or validation of the input data before processing.
Audit Metadata