consult-brd-writer
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from shadowing transcripts and external Google Docs (Ingestion points: Workflow Step 1).
- Boundary markers: There are no explicit markers or instructions used to delimit untrusted external content within the prompts.
- Capability inventory: The skill possesses the ability to write to Google Docs and update CRM deal notes via MCP tools (
mcp__google-workspace__create_doc,mcp__zynkr__update_deal). - Sanitization: The risk is partially mitigated by a requirement to summarize raw data into 'process segments' before final extraction (Workflow Step 1) and a mandatory human-in-the-loop approval gate for the document outline (Workflow Step 4).
- [EXTERNAL_DOWNLOADS]: The documentation includes a command to install the skill using
npxfrom the author's repository (https://github.com/peter-tu-zynkr/zynkr-skill-builder). This is a standard installation pattern for this author's environment. - [COMMAND_EXECUTION]: The installation instructions involve the use of
npx, which executes code from a remote repository.
Audit Metadata