ask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
54
61%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Fix and improve this skill with Tessl
tessl review fix ./.agents/skills/ask-matt/SKILL.mdThe canonical home for this skill is ask-matt in mattpocock/skills
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 "/wizard" explicitly instructs the agent to generate an interactive script that "captures each value" and writes them into .env and GitHub secrets, which implies handling user secrets and could lead the LLM to request, process, or embed secret values verbatim.
- Repository
- The-Vibe-Company/companion
- Commit
8d000e5
- 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.