implement-issue

Warn

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions recommend using GIT_SSL_NO_VERIFY=1 for network operations within sandbox environments. Disabling SSL/TLS verification removes protection against Man-in-the-Middle (MitM) attacks, which could allow an attacker to intercept or modify data transmitted between the agent and GitHub.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from external GitHub issues that can contain malicious instructions intended to hijack the agent's logic during the planning or implementation phases.
  • Ingestion points: External data is ingested via the gh issue view <url-or-number> command in SKILL.md.
  • Boundary markers: Absent. The skill does not define delimiters or provide instructions to ignore potential commands embedded within the issue text.
  • Capability inventory: The skill possesses significant capabilities, including local file writes (_/local-plans/), modification of source code, execution of project-specific test commands, and the ability to create commits.
  • Sanitization: There is no evidence of sanitization or structural validation performed on the issue content before it is processed by the model to generate code changes.
Audit Metadata
Risk Level
MEDIUM
Analyzed
May 16, 2026, 07:51 AM
Security Audit — agent-trust-hub — implement-issue