trading-ledger
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection via user-provided trade data.
- Ingestion points: Untrusted data enters the agent context through user trade reports described in the 'Overview' and 'Step 2' of SKILL.md (e.g., thesis, plan, and trade notes).
- Boundary markers: The instructions lack specific delimiters or guidelines for the agent to distinguish between user-provided data and control instructions, nor does it include 'ignore embedded instructions' warnings.
- Capability inventory: The skill uses the Notion connector for tool calls including
search,query,create-pages, andupdate-pageto manage the ledger. - Sanitization: There is no mention of sanitizing, filtering, or validating external content before it is interpolated into queries or page creation tools.
Audit Metadata