conventional-commits
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from local file changes, which creates a surface for indirect prompt injection where malicious instructions inside a file could manipulate the AI's behavior.
- Ingestion points: The output of the "git diff --staged" command is used as the primary input for analysis (SKILL.md).
- Boundary markers: The instructions do not define clear delimiters or warnings to ignore embedded instructions within the diff content.
- Capability inventory: The skill is focused on text generation and does not have secondary capabilities like network access or arbitrary code execution.
- Sanitization: No filtering or sanitization is performed on the content of the staged changes before processing.
- [COMMAND_EXECUTION]: The skill requires the execution of the "git diff --staged" command on the local system. This is an expected and necessary operation for the skill's core functionality.
Audit Metadata