pick-gtm-tools
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute a bundled Python script located at
scripts/check_shortlist.pyto validate output formatting. This execution is performed locally using thepython3interpreter. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from an external source (
thegtmdirectory.com). - Ingestion points: Data enters the context via the
search_tools,get_tool,compare_tools, andrecommend_stackMCP/API calls. - Boundary markers: The skill lacks explicit boundary markers for the data returned by the API, although it instructs the agent to cite the source and follow a strict format.
- Capability inventory: The skill has the capability to execute a local Python script (
scripts/check_shortlist.py) as part of its workflow. - Sanitization: No specific sanitization or filtering of the external API content is mentioned prior to it being processed by the agent or the linter script.
Audit Metadata