ci-pipeline-monitor
Monitors .NET runtime CI test pipelines on Azure DevOps. Use this skill when asked to monitor CI pipeline test results, triage CI test failures across ADO pipelines, or generate CI test monitoring reports.
73
92%
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
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 prompt requires the agent to obtain and pass the ADO_TOKEN bearer token (including explicitly "Pass the `ADO_TOKEN` to each sub-agent"), which forces the LLM workflow to handle and transmit a secret value that could be output verbatim.
Low
Low-risk findings.
2 low severity findings. 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
High likelihood: during the required “Triage Failures (agent)” step the LLM reads/verbatim-extracts `error_message`/`stack_trace` (from AzDO Test Results API) and the full Helix console log text from disk into its context, and those console/log/error strings are outsider-authored CI failure output (from AzDO public project + Helix logs) that can include prompt-injection text.
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
The file references/prerequisites.md (lines 29-31) instructs running "curl -sL https://aka.ms/InstallAzureCLIDeb | sudo bash" which fetches and executes a remote install script at runtime, representing a high-risk remote code execution dependency (https://aka.ms/InstallAzureCLIDeb).
- Repository
- dotnet/runtime
- Commit
ba10a6e
- 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.