skills/afonsoft/skills/create-issues/Gen Agent Trust Hub

create-issues

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill performs expected operations using the official GitHub CLI to manage repository issues based on local documentation. All identified actions align with the skill's stated purpose and follow legitimate developer workflows.
  • [COMMAND_EXECUTION]: Employs standard GitHub CLI ('gh') commands for repository management, issue creation, and label management. These commands are executed within the user's authenticated environment for project tracking.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local roadmap and specification files to generate issue metadata. 1. Ingestion points: Reads contents from 'ORCHESTRATOR-ROADMAP.md', '.specs/SPEC-*.md', and 'docs/architecture/'. 2. Boundary markers: No explicit delimiters or warnings to ignore embedded instructions are present in the documentation ingestion process. 3. Capability inventory: Uses 'gh issue create', 'gh issue edit', and 'gh label create' to write to GitHub. 4. Sanitization: The skill maps text directly to issue titles and bodies without specific sanitization steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 01:05 AM
Security Audit — agent-trust-hub — create-issues