verify-and-ship

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface identified where external untrusted data influences agent actions.
  • Ingestion points: The skill fetches acceptance criteria and issue details using the get_issue tool (SKILL.md).
  • Boundary markers: None identified; external issue content is processed directly without delimiters or instructions to ignore embedded commands.
  • Capability inventory: The skill executes shell commands (ls, git diff, git push) and uses CLI tools for PR/MR management (gh, glab) (SKILL.md).
  • Sanitization: There is no evidence of sanitization, validation, or escaping of the fetched issue content before it is used to verify requirements or generate PR descriptions.
  • [COMMAND_EXECUTION]: The skill uses local shell commands for repository management and interaction with GitHub/GitLab CLI tools. These operations are within the stated purpose of the skill but are part of the capability inventory accessible to potential indirect injections.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 06:04 PM
Security Audit — agent-trust-hub — verify-and-ship