pull-request-elegant
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill automates various Git and Azure CLI operations. It runs commands such as
git status,git log,git diff, andgit pushto manage local repository state. It also utilizes theazCLI for managing Azure DevOps resources, includingaz boards work-item showandaz repos pr createas documented in SKILL.md. - [PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection (Category 8). It processes external, potentially untrusted data from git commit messages and diffs to generate content for pull request titles and descriptions.
- Ingestion points: Data is ingested from
git logandgit diffoutputs within the local repository environment as specified inSKILL.md. - Boundary markers: While the skill employs structured templates and conventional commit formats, it lacks explicit instructions to treat the ingested commit history as untrusted or to ignore embedded instructions.
- Capability inventory: The skill possesses significant capabilities, including the ability to write to remote repositories and transition work items using the
azCLI, as documented across several sections ofSKILL.md. - Sanitization: The skill instructions do not specify any sanitization, filtering, or escaping mechanisms to be applied to the ingested git metadata before it is interpolated into CLI command arguments.
Audit Metadata