press-release-writer
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely composed of Markdown-based guidance and text templates. It contains no executable scripts (Python, JavaScript, shell), binary files, or automated command execution logic.
- [SAFE]: No hardcoded secrets, API keys, sensitive system file paths, or network exfiltration patterns were found. All URLs in the templates are generic placeholders (e.g., [URL]) meant for user customization.
- [SAFE]: The instructions do not attempt to bypass LLM safety guardrails or override system prompts. The role-play elements are standard for persona-driven text generation and do not include jailbreak attempts.
- [SAFE]: Indirect Prompt Injection surface: (1) Ingestion points: The skill accepts user-provided drafts and briefs as specified in SKILL.md. (2) Boundary markers: No explicit input delimiters or sanitization warnings are present. (3) Capability inventory: The skill has no capabilities to execute code, access the file system, or make network calls. (4) Sanitization: No validation logic is implemented. Although the skill processes external data, the lack of dangerous capabilities ensures that any potential injection is non-exploitable and safe.
Audit Metadata