github-automation

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from GitHub which creates a surface for indirect prompt injection attacks.
  • Ingestion points: The agent ingests untrusted content through tools such as GITHUB_LIST_REPOSITORY_ISSUES (issue bodies/comments), GITHUB_GET_A_PULL_REQUEST (PR descriptions), and GITHUB_SEARCH_CODE (external source code).
  • Boundary markers: The instructions do not specify the use of delimiters, XML tags, or explicit 'ignore' instructions to prevent the agent from following commands embedded in the retrieved GitHub data.
  • Capability inventory: The skill possesses high-privilege capabilities including merging pull requests (GITHUB_MERGE_A_PULL_REQUEST), triggering CI/CD workflows (GITHUB_CREATE_A_WORKFLOW_DISPATCH_EVENT), and deleting repositories (GITHUB_DELETE_A_REPOSITORY).
  • Sanitization: No sanitization, filtering, or validation steps are defined for the data retrieved from GitHub before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 03:04 PM
Security Audit — agent-trust-hub — github-automation