anki
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFENO_CODE
Full Analysis
- SAFE (SAFE): No malicious patterns or security risks detected. The skill is entirely declarative.
- NO_CODE (SAFE): The skill contains no executable code files (.py, .js, .sh, etc.), relying solely on Markdown instructions to guide the agent's behavior.
- DATA_EXFILTRATION (SAFE): No network or file-system capabilities exist that would allow for the unauthorized transmission of data.
- PROMPT_INJECTION (SAFE): The instructions do not contain any patterns intended to bypass safety filters or override system prompts.
- INDIRECT_PROMPT_INJECTION (SAFE): While the skill ingests untrusted user data (Source Material in SKILL.md), it possesses no capabilities (no subprocesses, no network, no file-writing) to exploit. Grounding instructions serve as basic boundary markers.
Audit Metadata