company-announcement-writer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill is composed entirely of markdown instructions and lacks any executable components, scripts, or configuration files that could execute commands.- [DATA_EXFILTRATION] (SAFE): No hardcoded credentials, sensitive file paths, or network-connected commands (e.g., curl, wget) were detected.- [INDIRECT_PROMPT_INJECTION] (LOW): This skill has a surface for indirect prompt injection but no capabilities to exploit. 1. Ingestion points: The skill processes user-provided context to generate announcements in SKILL.md. 2. Boundary markers: No delimiters are used to separate user data from instructions. 3. Capability inventory: No subprocesses, file system access, or network operations are available. 4. Sanitization: No input validation is performed.
Audit Metadata