skills/alexandru/skills/code-review/Gen Agent Trust Hub

code-review

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external and potentially untrusted data including code diffs, file contents, and pull request metadata to perform its review. This creates an attack surface where a malicious actor could embed instructions within the code or metadata to subvert the agent's review logic or safety guidelines.\n
  • Ingestion points: The skill ingests staged/unstaged diffs, untracked files, commit metadata, and pull request context from external repositories (SKILL.md).\n
  • Boundary markers: The instructions do not specify explicit boundary markers or directives to ignore instructions embedded within the reviewed code.\n
  • Capability inventory: The agent uses tools to read file contents, browse the codebase context, and perform web searches to facilitate the review process (SKILL.md).\n
  • Sanitization: The instructions do not specify any validation or sanitization steps for the external code or metadata being processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 10:44 AM
Security Audit — agent-trust-hub — code-review