skills/datadog-labs/pup/dd-file-issue/Gen Agent Trust Hub

dd-file-issue

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the gh (GitHub CLI) tool to perform repository searches and issue creation (e.g., gh issue create, gh issue list). It also executes pup --version to gather environment data. These operations are essential for the skill's primary function and target well-known Datadog repositories.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) because it accepts arbitrary user input to populate the title and body of GitHub issues.
  • Ingestion points: User-provided bug reports, feature requests, and environment details in SKILL.md.
  • Boundary markers: The skill uses an 'Issue Body Template' to structure input, though it does not implement strict sanitization logic for the content itself.
  • Capability inventory: The skill has the capability to write to external repositories via gh issue create and read issue lists via gh issue list.
  • Sanitization: There is no explicit sanitization or escaping of user input before it is passed to the shell via the gh command, which is a common characteristic of such agent skills.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 02:09 AM