code-reviewer
Fail
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: CRITICALMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [METADATA_POISONING]: The skill's documentation link ('https://jeffallan.github.io/claude-skills/skills/quality/code-reviewer/') is blacklisted and flagged as malicious by automated URL scanners.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content, such as source code and pull request descriptions, making it susceptible to indirect prompt injection where malicious instructions could be hidden in the code.
- Ingestion points: Pull request descriptions and source code files retrieved using the 'Read', 'Grep', and 'Glob' tools (SKILL.md, Workflow Step 1).
- Boundary markers: The skill does not provide delimiters or specific instructions for the agent to separate untrusted data from the reviewer's instructions.
- Capability inventory: The skill utilizes the 'Read', 'Grep', and 'Glob' tools to search and analyze project files for the purpose of generating review reports.
- Sanitization: No sanitization or validation of the ingested external content is performed.
Recommendations
- AI detected serious security threats
- Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata