custom-investigation
Run a custom investigation: review a chosen slice of conversations instead of a random sample, by writing a SQL selector over the observed agent's telemetry, and optionally narrow what the reviewer reports. Use when a message asks to investigate only certain conversations -- ones that hit an error, used a particular tool, ran slowly, mention a topic, looped, or were abandoned -- or asks to re-review conversations already seen with a different focus. Covers the telemetry table a selector reads, writing the selector, previewing what it matched, and starting the run.
96%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Medium
Suggest reviewing before use
W009: Direct money access capability detected (payment gateways, crypto, banking).
What this means
The skill is specifically designed for direct financial operations, giving the agent the ability to move money or execute financial transactions — such as payment processing, cryptocurrency operations, banking integrations, or market order execution.
Why it was flagged
The skill operates a custom investigation workflow over agent telemetry via tools such as `preview_custom_investigation` and `start_custom_investigation`. It mentions a BigQuery bill in documentation context, but this is a service cost / operational resource billing notice rather than an explicit user-facing direct financial transfer, charge, or trade instruction. Therefore, the financial operation is indirect (submitting usage/query execution costs downstream for billing), and the severity is medium.
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 instructs the agent to query conversation telemetry/logs containing user messages and chat inputs from BigQuery/Cloud Logging/Cloud Ops, which are populated by external users, representing an indirect prompt injection risk via monitored chat data.
- 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.