create-pr
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
gitandgh(GitHub CLI) commands to inspect the repository, push branches, and create pull requests. These operations are essential for the skill's primary function of PR automation. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from commit logs and git diffs to automatically compose PR titles and summaries, creating a potential surface for indirect prompt injection if the repository history contains malicious instructions.
- Ingestion points:
git logandgit diffoutputs are used as context inSKILL.md. - Boundary markers: No explicit delimiters or "ignore instructions" markers are used when processing the git data.
- Capability inventory: The skill has network-write capabilities via
git pushandgh pr createas seen inSKILL.md. - Sanitization: No sanitization or validation is applied to the retrieved git content before it is processed by the agent.
Audit Metadata