teams-channel-post-writer
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE] (SAFE): No malicious patterns detected. The skill consists of markdown templates and instructional text for writing documentation.\n- [NO_CODE] (SAFE): This skill contains no executable scripts (Python, JavaScript, Shell, etc.). It is purely a prompt-based writing assistant.\n- [DATA_EXFILTRATION] (SAFE): No network operations or credential access found. The skill instructions suggest local file saving for documentation purposes, which is consistent with its stated purpose.\n- [INDIRECT_PROMPT_INJECTION] (SAFE): Although the skill involves researching external documentation, there are no exploitable capabilities (like arbitrary command execution or network exfiltration) that would allow an external prompt injection to cause significant harm. The process includes verification steps that act as a safeguard.
Audit Metadata