raise-issue
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
git,gh,glab, andteaCLI tools to retrieve remote repository URLs and create issues on external hosting platforms. These are legitimate development tools used according to their intended purpose. - [PROMPT_INJECTION]: Indirect Prompt Injection Surface: The skill ingests untrusted user input to generate issue documentation that is persisted locally and remotely.
- Ingestion points: User-provided issue titles, descriptions, and context are processed in Step 3 and Step 6 during file creation and CLI execution.
- Boundary markers: The template uses standard markdown headers but lacks explicit boundary markers or instructions for the agent to ignore embedded commands within the issue body.
- Capability inventory: The agent has the capability to write to the local filesystem (
llmwiki/wiki/sources/) and execute shell commands via CLI tools. - Sanitization: There is no evidence of input sanitization or validation before the content is written to files or passed to shell command arguments.
Audit Metadata