dd-file-issue
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the
gh(GitHub CLI) tool to list and create issues in theDataDog/pupandDataDog/datadog-api-claude-pluginrepositories. - [DYNAMIC_EXECUTION]: The instructions provide shell command templates in
SKILL.mdthat the agent is expected to populate with user-supplied strings (such as issue titles and descriptions) at runtime. This represents a simple script generation pattern from templates. - [INDIRECT_PROMPT_INJECTION]: The skill creates a vulnerability surface by ingesting untrusted user input and interpolating it into shell commands without explicit safety instructions.
- Ingestion points: User-provided text for issue titles, descriptions, and environment details gathered during the "Gather Information" workflow step.
- Boundary markers: Absent; the instructions do not specify the use of delimiters or provide warnings to ignore instructions embedded within the user's issue report.
- Capability inventory: Execution of
gh issue createandgh issue listshell commands as documented in the "Implementation" section. - Sanitization: The instructions do not recommend escaping, validating, or filtering the user-provided content before it is used as an argument in the shell command templates.
Audit Metadata