skills/coroboros/agent-skills/forge/Gen Agent Trust Hub

forge

Pass

Audited by Gen Agent Trust Hub on Jul 4, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes local shell and Python scripts for administrative tasks such as setting up GitHub labels and validating the technical specification against a predefined schema. These scripts are included in the skill's own directory.
  • [EXTERNAL_DOWNLOADS]: Research capabilities are supported through the use of WebFetch and the GitHub CLI to retrieve content from external URLs and issues, facilitating data-driven decision-making. These operations are essential for the skill's stated purpose.
  • [PROMPT_INJECTION]: The skill processes content from potentially untrusted external sources like web pages and GitHub issues. This creates an indirect prompt injection surface; however, the skill explicitly provides templates and instructions for wrapping such data in XML tags within subagent prompts to prevent the content from being interpreted as instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 4, 2026, 01:31 PM
Security Audit — agent-trust-hub — forge