coding-standards-enforcer
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and review external Swift source code, which serves as a potential vector for instructions hidden in code comments or strings intended to subvert agent behavior.
- Ingestion points: External Swift source files provided by the user for review or migration (documented in
SKILL.md). - Boundary markers: The instructions do not define specific delimiters or "ignore" instructions to separate the source code content from the agent's logic.
- Capability inventory: The agent is instructed to "Fix or flag deviations explicitly," which implies file-writing or code-generation capabilities (
SKILL.md). - Sanitization: There is no explicit sanitization or validation of the input source code to filter out potentially malicious natural language instructions.
Audit Metadata