skills/hkuds/deepcode/review-agent/Gen Agent Trust Hub

review-agent

Warn

Audited by Gen Agent Trust Hub on Nov 7, 2026

Risk Level: MEDIUMMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
  • [METADATA_POISONING]: The file LICENSE.txt includes a copyright notice for 'OpenAI', which contradicts the provided author information ('hkuds'). This deceptive claim can mislead users into believing the skill is an official or trusted product from a well-known organization.
  • [INDIRECT_PROMPT_INJECTION]: The skill's design involves reading untrusted content which can contain malicious instructions. Ingestion points: The skill is instructed in SKILL.md to read the AGENTS.md file and code diffs from the repository. Boundary markers: There are no markers or instructions provided to separate the system prompt from potentially adversarial instructions in the repository files. Capability inventory: The skill uses git merge-base and git diff for inspecting repository state. Sanitization: No sanitization or validation is applied to the content retrieved from the files being reviewed.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 7, 2026, 06:32 AM