tool-selection-stack
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a local utility script
scripts/check-output.py. This script is used to verify that the agent's output contains specific required sections (e.g., '## Context', '## Metrics'). It uses standard Python libraries (pathlib,sys) to read a file and check for substrings. It does not perform network operations, access sensitive files, or execute arbitrary code. - [EXTERNAL_DOWNLOADS]: The playbook in
references/gtm-automation-expert-playbook.mdcontains links to external resources, including the vendor's own GitHub repository (github.com/LeadMagic/gtm-skills) and professional profiles (LinkedIn, Go Nimbly). These are standard references for a GTM advisory skill and do not involve executable code downloads. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user requirements (e.g., 'Build my GTM stack') and use them to populate a structured template (
templates/output-template.md). While it processes user-provided data, it does not involve untrusted data sources like web scraping or third-party API payloads that could be used for injection. The risk is minimized by the use of a fixed output template and internal framework references.
Audit Metadata