Skills
Navigate
skills/wkentaro/skills/sending-pull-request/Gen Agent Trust Hub

sending-pull-request

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill generates Pull Request titles and bodies by interpreting potentially untrusted data from the repository, such as git diffs and commit history.
  • Ingestion points: Data is ingested via git diff and git log commands in SKILL.md step 4.
  • Boundary markers: The skill does not provide specific delimiters or instructions to help the agent distinguish between legitimate code changes and malicious instructions embedded in the diffs.
  • Capability inventory: The skill has the capability to write to the repository forge using git push and gh pr create/edit in SKILL.md steps 5 and 6.
  • Sanitization: There are no explicit sanitization or filtering steps applied to the ingested content before it is used to generate the PR body.
  • [COMMAND_EXECUTION]: The skill executes various shell commands to manage the git environment and interact with the GitHub CLI.
  • Evidence: SKILL.md contains commands for git switch, git branch, git push, and gh pr create with file attachments.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 06:40 AM
Security Audit — agent-trust-hub — sending-pull-request