skill-writing
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- Prompt Injection (SAFE): No attempt to override agent instructions or bypass safety filters was detected. The content is focused on providing structural guidance and templates.
- Data Exposure & Exfiltration (SAFE): The skill does not access local files, environment variables, or hardcoded secrets. No network communication logic is present.
- Unverifiable Dependencies & Remote Code Execution (SAFE): No package managers (pip, npm) or remote script downloads (curl | bash) are used. While it mentions the use of scripts in a design context, it does not provide or execute them.
- Obfuscation (SAFE): No base64, zero-width characters, or homoglyph-based evasion techniques were identified.
- Indirect Prompt Injection (INFO): The skill handles user-provided requirements to generate markdown files. Because this skill lacks side-effect capabilities such as file-system writes, command execution, or network requests, the risk of an indirect injection causing harm to the host system is negligible.
- Privilege Escalation & Persistence (SAFE): No system-level commands (sudo, chmod) or persistence mechanisms (cron, registry) are utilized.
Audit Metadata