golang-code-review

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to analyze and review Go code provided in pull requests or files, which are untrusted external data sources. This creates a surface for indirect prompt injection where malicious instructions could be embedded within code comments or logic to influence the agent's review behavior.
  • Ingestion points: The review workflow described in SKILL.md involves reading and evaluating code snippets or full PRs provided in the agent's execution context.
  • Boundary markers: The skill instructions do not mandate the use of delimiters or specific prompts to distinguish the code being reviewed from the agent's own instructional logic.
  • Capability inventory: The skill focuses on generating text-based feedback. No scripts or instructions within the skill files invoke dangerous capabilities such as direct shell execution, file-system modification, or unauthorized network access.
  • Sanitization: There are no instructions or mechanisms provided to sanitize or filter the content of the analyzed code before it is interpreted by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 03:43 PM
Security Audit — agent-trust-hub — golang-code-review