refactor-telemetry-plan
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates as an advisory documentation tool that evaluates the impact of code changes on analytics dashboards and funnels. It does not possess capabilities to modify code or communicate with external servers.
- [COMMAND_EXECUTION]: The script
scripts/checklist.mjsutilizesexecFileSyncto rungit diff. This is a standard and safe operation within a developer environment to identify code changes for analysis. - [PROMPT_INJECTION]: The skill processes untrusted input in the form of code diffs. While this presents a surface for indirect prompt injection, the risk is categorized as low because the skill is explicitly restricted to generating a tracking plan and risk table, with no permissions to execute the proposed changes or perform network actions.
Audit Metadata