skills/narasaka/skills/file-pr/Gen Agent Trust Hub

file-pr

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from user prompts and local file diffs to generate PR titles and descriptions, creating a surface for potential instruction injection via data processed at runtime.
  • Ingestion points: User prompts and local repository diffs (SKILL.md).
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the ingested data.
  • Capability inventory: The skill utilizes shell command execution via the gh CLI to create pull requests and interact with the GitHub API (SKILL.md).
  • Sanitization: There are no explicit instructions to sanitize or escape external content before it is used as arguments in shell commands or interpolated into the PR description.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the GitHub CLI (gh pr create, gh api) to manage repository state.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 04:02 AM