Skills
Navigate
skills/jetbrains/skills/gh-address-comments/Gen Agent Trust Hub

gh-address-comments

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONPRIVILEGE_ESCALATION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from GitHub PR comments, which are external and could contain embedded instructions.
  • Ingestion points: Data is fetched from the GitHub API in scripts/fetch_comments.py via the gh api graphql command.
  • Boundary markers: The instructions in SKILL.md do not specify delimiters or instructions to ignore potential commands embedded within PR comments.
  • Capability inventory: The skill is authorized in SKILL.md to 'Apply fixes', which involves code modifications and gh/git command execution.
  • Sanitization: The script scripts/fetch_comments.py performs no sanitization or validation of the comment content before the agent processes it.
  • [COMMAND_EXECUTION]: The skill relies on the GitHub CLI (gh) to perform its functions.
  • Execution is managed in scripts/fetch_comments.py using subprocess.run with list-based arguments, which is a standard security practice to mitigate injection risks.
  • [PRIVILEGE_ESCALATION]: The skill requests elevated permissions via sandbox_permissions=require_escalated in SKILL.md to ensure the gh CLI has sufficient access to authentication states and repository data.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 04:24 PM