make-it-right
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external code changes which may contain text intended to influence the agent (Indirect Prompt Injection). The skill mitigates this risk by providing specific instructions in
references/findings.md(Rule 0) that explicitly direct the agent to treat the code under review as data and ignore any instructions found within it. - [COMMAND_EXECUTION]: The skill executes local Git commands and development scripts (
scripts/new_lines.sh,scripts/snapshot.sh) to gather information about code changes and maintain state. It also triggers standard development tools likerspecandrubocopfor testing and linting, as defined in the stack configuration.
Audit Metadata