company-announcement-writer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): The instructions are limited to drafting corporate announcements. No jailbreak, role-play, or override patterns detected.
- [Data Exposure & Exfiltration] (SAFE): No credentials, sensitive file paths, or network operations are present in the skill.
- [External Downloads & RCE] (SAFE): The skill does not install third-party packages or execute remote scripts.
- [Indirect Prompt Injection] (SAFE): The skill ingests untrusted user data via prompts (ingestion: SKILL.md). While boundary markers and sanitization are absent, the skill inventory shows no capabilities (no subprocess calls, no file-write, no network operations), rendering injection non-exploitable.
- [No Code] (SAFE): The skill consists entirely of natural language instructions and contains no executable logic.
Audit Metadata