code-review
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted external code as part of its core functionality without implementing specific isolation techniques.\n
- Ingestion points: User-provided code snippets, pull request content, and uploaded source files are processed as directed in SKILL.md.\n
- Boundary markers: Absent. The skill's instructions do not mandate the use of delimiters (such as XML tags or triple backticks) or explicitly warn the agent to ignore instructions embedded within the code being analyzed.\n
- Capability inventory: The skill logic includes comprehensive code analysis and recommends the use of external static analysis tools, providing a pathway for manipulated agent behavior if malicious instructions are present in the code comments or strings.\n
- Sanitization: Absent. The instructions do not describe any sanitization, validation, or escaping of user content prior to processing.
Audit Metadata