unstuck
Break through stagnation with lateral thinking personas — single or multi-persona debate
56
63%
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 ./.claude-plugin/skills/unstuck/SKILL.mdThe canonical home for this skill is unstuck in Q00/ouroboros
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
This SKILL instructs the agent to collect user-provided fields (problem_context / current_approach), place them verbatim into MCP payloads and an appended base64-encoded inline-dispatch block, and pass payload.prompt + payload.context verbatim to subagents — so any secrets the user puts into those fields would be embedded in the LLM's output (visible markdown or the HTML-comment/base64 block), creating a direct exfiltration risk.
- Repository
- Q00/ouroboros
- Commit
80333ae
- 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.