compose:debug
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill's diagnostic examples instruct logging environment variables and run commands like `env | grep IDENTITY` (which will print secret values) and include a `codesign --sign "$IDENTITY"` usage, meaning the prompt encourages reading and emitting secret values during diagnostics.
- Repository
- XiaomiMiMo/MiMo-Code
- Commit
ec3f989
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.