rei
Set up Rei Qwen3 Coder as a model provider. Use when configuring coder.reilabs.org, adding Rei to Clawdbot, or troubleshooting 403 errors from Rei endpoints.
92
88%
Does it follow best practices?
Impact
100%
1.66xAverage score across 3 eval scenarios
High
Do not use without reviewing
Security
2 findings: 1 high severity, 1 medium severity. 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 directly instructs the agent to accept and embed an API key verbatim into commands and config (e.g., "./skills/rei/scripts/setup.sh YOUR_REI_API_KEY" and the "apiKey" field), which requires the LLM to handle secrets in its output.
W013: Attempt to modify system services in skill instructions.
What this means
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Why it was flagged
The skill explicitly instructs the agent to run setup scripts that modify configuration files (e.g., ~/.clawdbot/clawdbot.json), add providers/allowlists, and restart the gateway — actions that change the machine's state — though it does not request sudo, create users, or bypass security mechanisms.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The skill explicitly configures and directs the agent to use an external model endpoint (https://coder.reilabs.org/v1) — see SKILL.md manual setup and scripts/setup.sh where REI_PROVIDER is added — so the agent will ingest and act on untrusted third‑party model outputs that could alter its actions.
- Repository
- Demerzels-lab/elsamultiskillagent
- Commit
f45fcb5
- 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.