conclave-skill@1.6.7
CAUTION· install onlyPublisher claims: "Conclave is a multi-agent reasoning skill that orchestrates multiple AI CLIs into structured debates. Each agent independently analyzes the problem, challenges competing arguments, identifies flaws and contradictions, and refines the reasoning through multiple rounds of discussion — helping you reach more reliable conclusions than relying on a single AI." Observed in sandbox: reads credential files.
Coverage
Install scripts ran; no agent task scenario for this bundle.- Tested
- install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; install scripts ran; no agent task scenario for this bundle) on 2026-11-09 and scored it 71/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Privileged sudo command; Privileged sudo command; Latin word with Cyrillic or Greek look-alike letters (homoglyph). Summary: reads credential files.
Behavior trace
Honeypot run · 17 s · 2 scenariosStatic findings
sudo dnf install -y nodejs npmFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.- Command: `no_proxy='*' claude -p '<prompt>' --max-turns 1`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- Command: `no_proxy='*' qwen -p '<prompt>'`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.sudo apt-get update -qq && sudo apt-get install -y nodejs npmFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.ΣŵᵢFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.try_update qwen npm install -g @qwen-code/qwen-code@latestFix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.try_update gemini npm install -g @google/gemini-cli@latestFix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.- Command: `no_proxy='*' GEMINI_CLI_TRUST_WORKSPACE=true zsh -i -c 'gemini -p "<prompt>"'`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…s good") → never auto-scored; only post-hoc qualitative review. The system must never refuse hard strategic questions just because they are unscoreable. ## 11a. Research d…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- Command: `no_proxy='*' codex exec --skip-git-repo-check -c model_reasoning_effort="medium" '<prompt>'`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.try_update codex npm install -g @openai/codex@latestFix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.info "installing node via dnf (may prompt for sudo password)..."Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.ρᵢⱼFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.λΣρᵢⱼwⱼFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.ΣŵᵢFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.info "installing node via apt-get (may prompt for sudo password)..."Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.[ -f "$HOME/.claude/.credentials.json" ] && CLAUDE_CRED=1Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- Command: `deepcode-panelist '<prompt>'`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
9 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Reads credential files≈ +27 on the totalThe sandbox saw reads under ~/.ssh, ~/.aws, ~/.npmrc, ~/.config or similar. Read only files inside the project, and only the ones the task needs. Seen: ~/work/acme-api/.npmrc, ~/.npmrc.
- Unclaimed publisher≈ +8 on the totalClaim mclyang: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
- Unpinned dependencies≈ +4 on the totalPin exact versions (and ideally hashes) in package.json, requirements or the install script so the bundle cannot change under you.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.