skills/aws-samples/sample-aidlc-toolset-with-subagents-and-custom-skills/git-merge/Gen Agent Trust Hub
git-merge
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard, non-privileged git commands (
git status,git diff,git log) to identify merge conflicts and retrieve version history. This behavior is consistent with the stated purpose of resolving source control conflicts. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from incoming git branches and project design artifacts to resolve conflicts.
- Ingestion points: Conflicted files (
aidlc-state.md,audit.md) and application code files as described inSKILL.mdand the referenced merge strategy documents. - Boundary markers: The instructions do not specify explicit delimiters or "ignore previous instructions" warnings when the agent reads external file content for analysis.
- Capability inventory: The skill has access to shell commands (
git) and file system read/write operations within the project directory. - Sanitization: There is no explicit sanitization of the content found within the conflicted files before the agent parses them for resolution logic.
- Note: This represents a documented attack surface inherent to tools that analyze and merge external source code; however, no malicious intent was observed.
Audit Metadata