onboarding
Deploy your own Open-Inspect instance. Use when the user wants to set up, deploy, or onboard to Open-Inspect. Guides through repository setup, credential collection, Terraform deployment, and verification with user handoffs.
89
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Security
3 findings — 1 high severity, 2 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
Insecure credential handling detected (high risk: 1.00). This prompt explicitly instructs collecting secrets from the user and embedding/printing them verbatim in files and commands (e.g., tfvars with access_key/secret_key, modal token set --token-secret, cat’ing converted .pem, echoing generated keys), which forces the LLM to handle/output secrets directly and creates a high exfiltration risk.
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
Third-party content exposure detected (high risk: 0.90). The guide explicitly provisions GitHub and Slack bots and instructs configuring webhooks and "Comment Actions: @mention the bot in a PR comment with instructions" (Phase 9/10 and GitHub App setup), so the deployed agent is expected to read untrusted, user-generated GitHub PR comments and Slack messages via webhooks which can materially influence its actions.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Potentially malicious external URL detected (high risk: 0.90). The skill instructs at runtime to git clone and build the remote repository git@github.com:ColeMurray/open-inspect.git, which fetches external code that is then built/executed and can directly control the agent's behavior.
- Repository
- ColeMurray/background-agents
- Commit
e5c55cf
- 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.