github-pr-issue

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes data from external sources (GitHub Issues and PRs), creating a surface for indirect prompt injection. Ingestion points: Reads titles, descriptions, comments, and diffs from GitHub as specified in the description and update section. Boundary markers: Lacks delimiters or explicit instructions to isolate untrusted content from system instructions. Capability inventory: Executes GitHub CLI and Git commands to create or modify PRs and Issues. Sanitization: No filtering or validation of external content is performed.
  • [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands, specifically git status, git push, and GitHub CLI commands (gh), to manage repository resources and automate workflows.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 10:54 PM