ai-code-review

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill is composed entirely of markdown instructions (SKILL.md) and does not include any scripts, binaries, or automated configuration files.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data such as code diffs and pull request descriptions. While this presents a potential attack surface, the skill lacks any capabilities (such as file writing, network access, or command execution) that could be leveraged for malicious purposes.
  • Ingestion points: Untrusted data enters the agent context through the Required Inputs section, which requests the diff or PR content.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the ingested data.
  • Capability inventory: No subprocess calls, network operations, or file system modifications are present in the skill.
  • Sanitization: There is no mention of sanitizing or escaping the provided diffs before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 05:56 PM
Security Audit — agent-trust-hub — ai-code-review