skills/remix-run/remix/update-pr/Gen Agent Trust Hub

update-pr

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the GitHub CLI (gh pr edit) to update pull request titles and descriptions. This is a standard operation for the stated purpose of managing PR metadata.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it incorporates untrusted external content into the agent's context.
  • Ingestion points: In SKILL.md, the workflow specifies reading the current PR title, body, and branch diff as primary inputs.
  • Boundary markers: No explicit delimiters (like XML tags or triple quotes) or negative constraints (like instructions to ignore embedded commands) are defined to separate the data from the agent's instructions.
  • Capability inventory: The agent has the authority to write back to the PR using the gh pr edit command, which could be abused if malicious instructions in a PR diff or body were obeyed.
  • Sanitization: The instructions lack input validation or filtering steps to ensure that content extracted from the PR does not influence the agent's operational logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 05:19 PM