Skills
skills/roger-235/my_skill_repo/product-discovery/Gen Agent Trust Hub

product-discovery

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local utility scripts/assumption_mapper.py using python3 to automate the prioritization of product assumptions. This script is part of the skill's distributed tooling.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from assumptions.csv, which serves as an entry point for untrusted content that could influence the agent's reasoning.
  • Ingestion points: Data from assumptions.csv or inline user input is passed to the scripts/assumption_mapper.py script.
  • Boundary markers: The skill does not specify delimiters or cautionary instructions for the agent when handling the content of the CSV file.
  • Capability inventory: The skill has the ability to execute shell commands (python3) and read files within the local environment.
  • Sanitization: There is no evidence of input validation or sanitization routines for the data processed during the assumption mapping phase.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 08:06 PM
Security Audit — agent-trust-hub — product-discovery