uinaf-radar
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local shell script scripts/check.sh which invokes gh (GitHub CLI) and jq. This is the primary mechanism for fetching status data and is used appropriately within the skill's scope.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface where it ingests untrusted data from GitHub. 1. Ingestion points: The scripts/check.sh script and suggested gh search commands in references/github.md ingest issue titles, pull request titles, and label names from external GitHub repositories. 2. Boundary markers: The instructions do not define explicit delimiters or instructions for the agent to ignore potentially malicious content within these titles. 3. Capability inventory: The agent has the ability to execute the scripts/check.sh script and various gh search and view commands. 4. Sanitization: No sanitization or filtering is performed on the retrieved text content before it is presented to the agent for summarization.
Audit Metadata