unblocked-context-engine
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were identified in the skill. The instructions focus on retrieving context for better code understanding.
- [COMMAND_EXECUTION]: The 'Tool Availability Safety Handler' provides logic for the agent to discover available tools via
listToolsif the primary tool is missing. This is an orchestration feature for cross-environment compatibility. - [PROMPT_INJECTION]: The skill facilitates indirect prompt injection surfaces by ingesting data from external sources.
- Ingestion points: External data (Slack threads, Jira issues, docs, and PRs) retrieved via the
unblocked_context_enginetool. - Boundary markers: Not present; the instructions do not specify delimiters or 'ignore' instructions for external content.
- Capability inventory: The agent environment typically includes file system access and shell execution capabilities for development tasks.
- Sanitization: No explicit sanitization or validation of the retrieved content is mentioned in the skill instructions.
Audit Metadata