issue-analysis

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) through bash commands to perform read and write operations on issues within the homeassistant-ai/ha-mcp repository.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from GitHub issue titles, descriptions, and comments.
  • Ingestion points: Issue metadata and content fetched via gh issue view and gh issue list in SKILL.md (Steps 1 and 3).
  • Boundary markers: None explicitly defined for external content ingestion.
  • Capability inventory: Includes filesystem access (Read, Glob, Grep), network access (WebFetch, WebSearch), and shell execution (Bash).
  • Sanitization: No programmatic sanitization is defined, but the skill mandates a human-in-the-loop confirmation step (Step 5) before the agent can post comments or apply labels, which serves as a security control against malicious automated actions. The instructions also warn the agent to treat issue content as potentially inaccurate.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 03:50 PM
Security Audit — agent-trust-hub — issue-analysis