skills/agenta-ai/agenta/write-issue/Gen Agent Trust Hub

write-issue

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill establishes clear guidelines for writing bug reports and feature requests. It leverages the GitHub CLI and project-specific MCP tools (mcp__linear-server__save_issue) to automate issue creation while maintaining consistent formatting.
  • [SAFE]: A significant security control is included: the agent is instructed to present a draft to the user and wait for approval before committing changes to Linear or GitHub. This human-in-the-loop requirement prevents the automated creation of malicious or incorrect issues from untrusted input.
  • [SAFE]: The resources and repositories referenced, such as the 'Agenta-AI/agenta' repository and the 'AGE' team key, are legitimate and correspond to the skill author's infrastructure, representing normal vendor functionality.
  • [SAFE]: Indirect Prompt Injection surface analysis: 1. Ingestion points: User requests to file bugs or feature requests (SKILL.md). 2. Boundary markers: The skill explicitly requires showing a draft to the user first. 3. Capability inventory: Bash access for GitHub CLI and Linear MCP tools. 4. Sanitization: Relies on human-in-the-loop verification of the draft before external tool execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 04:32 PM
Security Audit — agent-trust-hub — write-issue