wp-github-flow

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard system commands and command-line interfaces, including git for version control and gh for GitHub interaction. These are used for legitimate development tasks such as branching, committing, pushing, and merging pull requests.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of reading and processing untrusted external data.
  • Ingestion points: The agent is instructed to fetch and read GitHub issue titles, descriptions, and comments using gh issue view, as well as file diffs using git diff.
  • Boundary markers: The instructions do not define specific delimiters or boundary markers to separate untrusted external data from the agent's internal reasoning.
  • Capability inventory: The skill possesses significant capabilities, including the ability to execute shell commands, perform network operations (via git and gh), and modify the file system.
  • Sanitization: There is no mention of sanitizing or escaping the content retrieved from issues or diffs before processing.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with GitHub, which is a well-known and trusted service, for the purposes of code synchronization and issue management. This behavior is consistent with the skill's primary function.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 09:07 AM