press-release-creator
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): No malicious override instructions, safety bypass patterns, or system prompt extraction attempts were detected. The instructions are strictly focused on the document creation task.
- [Data Exposure & Exfiltration] (SAFE): No sensitive file paths, hardcoded credentials, or network operations were found. The skill only specifies saving the output to a local path (docs/press-release.md).
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): This is a 'No Code' skill consisting solely of Markdown instructions and templates. It does not install packages or execute external scripts.
- [Indirect Prompt Injection] (LOW): The skill ingests user input to populate templates. 1. Ingestion points: User dialogue for project details. 2. Boundary markers: Absent. 3. Capability inventory: File-write to local docs directory; no network or shell access. 4. Sanitization: Absent. There is no significant risk as the skill has no dangerous capabilities to exploit.
Audit Metadata