create-pr
Warn
Audited by Gen Agent Trust Hub on May 10, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to interact with the Git repository and the GitHub CLI (gh).
- [COMMAND_EXECUTION]: The skill explicitly suggests the use of
GIT_SSL_NO_VERIFY=1for Git and GitHub CLI operations in sandbox environments. Disabling SSL/TLS verification is a critical security bypass that eliminates protection against certificate spoofing and transport-layer interception. - [DATA_EXFILTRATION]: By recommending the disabling of SSL verification, the skill creates a condition where sensitive data, including GitHub authentication tokens and source code, can be intercepted by a network-level attacker during the
gh pr createorgit pushoperations. - [PROMPT_INJECTION]: The skill ingests untrusted data from git logs and diffs to generate PR summaries and titles, creating an indirect prompt injection surface.
- Ingestion points: Repository commit history and code diffs (SKILL.md Step 1 and 4).
- Boundary markers: Absent.
- Capability inventory: GitHub CLI operations (gh pr create) and Git repository modifications.
- Sanitization: Absent; the skill relies on internal model safety rather than data validation.
Audit Metadata