secure-code-review
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-supplied code snippets, which inherently creates a surface for indirect prompt injection where instructions embedded in the analyzed code could attempt to influence agent behavior. However, this is inherent to the skill's primary purpose as a code reviewer.
- Ingestion points: Code snippets or files provided by the user for security review (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or explicit warnings to the agent to ignore instructions found within the code being analyzed.
- Capability inventory: This skill does not include any executable scripts, network operations, or subprocess calls; it is purely instructional.
- Sanitization: There is no sanitization or filtering of the user-provided code mentioned in the instructions.
- [SAFE]: No other threat categories were identified. The skill contains examples of insecure code (e.g., hardcoded secrets, SQL injection, and unsafe deserialization), but these are clearly labeled as vulnerable and accompanied by secure remediation examples, which is standard for security training and auditing tools.
Audit Metadata