Repository navigation
Conversation
Refactor BQ skills
…ort support Added advanced diagnostic capabilities for agent reasoning paths and a new CLI command to export metrics to BigQuery for ML-driven evaluation
Query retrieves timestamps, agent IDs, and non-null retrieved documents, filtering based on specific patterns.
Updated the AgentSecurityAuditor to load threat patterns from SQL files in the 'patterns/' directory, with a fallback to default patterns. Enhanced the run_audit method to include the patterns used in the audit results.
Expanded the documentation for the GCP Agent Security Audit Skill, detailing its features, requirements, and usage instructions.
Refactor GCP Agent Security Audit Skill to enhance functionality and logging. Introduce new security patterns and improve log fetching and auditing processes.
Expanded the GCP Agent Security Audit Skill documentation with detailed features and examples for prompt injection, jailbreak, role override, indirect prompt injection, and data exfiltration detection. Updated requirements and usage instructions.
Updated SKILL.md to include new examples and detailed architecture flow for AI agent security monitoring.
|
Hi @Mhmda1998, thank you for this contribution! As explained in https://github.com/google/skills/blob/main/CONTRIBUTING.md#how-you-can-help, we're not accepting PRs for this repo currently. Your suggestion is valuable though, and we'd like to make sure that we internally triage it. Please feel free to post it as an issue in https://github.com/google/skills/issues. |
|
Hi @kumar-dhanagopal, thank you for the clarification. The proposal is already tracked in Issue #160, which specifically describes the gcp-agent-security-audit skill and its proposed BigQuery ML-based security auditing approach. PR #203 was created as the implementation of Issue #160 and includes the enhancements discussed in that issue. I’ll keep Issue #160 as the primary reference for the proposal and internal triage. Thank you for taking the time to review it. |
Closes #160
Description
Added the
gcp-agent-security-auditskill including:cc @gaurika-analyst