draft-security-advisory

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted vulnerability reports, creating a surface for indirect prompt injection where malicious instructions could influence the agent's behavior.\n
  • Ingestion points: Vulnerability reports enter the agent's context through file paths, pasted text, or GitHub advisory IDs as specified in the Inputs and argument-hint fields of SKILL.md.\n
  • Boundary markers: The instructions do not include boundary markers or explicit guidance for the agent to treat report content as untrusted or to ignore embedded instructions.\n
  • Capability inventory: The skill is granted significant capabilities including Bash (git, gh, and npm), Read, Write, Edit, and Agent tools, enabling it to perform file operations and network requests via the GitHub API.\n
  • Sanitization: There is no requirement for the agent to sanitize or validate the contents of the report before using it to investigate the codebase or construct command arguments.\n- [COMMAND_EXECUTION]: The skill executes multiple shell commands using the Bash tool. Several command arguments, such as code snippets for git log -S in Phase 3 or advisory IDs for gh api in Phase 1, are extracted directly from the untrusted vulnerability report, creating a potential for the agent to execute malformed or unintended commands based on manipulated input.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 12:13 PM