gtm-positioning
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Notion sub-pages (Step 01, 02, 03, and 05) which could potentially contain malicious instructions embedded by external actors or in previous workflow steps.
- Ingestion points: Reads competitor matrix, market ICP data, and client verbatim records from Notion.
- Boundary markers: No specific delimiters or warnings to ignore embedded instructions within the ingested data are present.
- Capability inventory: Performs read/write operations on Notion and reads local reference files in the plugin root.
- Sanitization: There is no evidence of data sanitization or validation before the content is processed by the agent.
Audit Metadata