designing-surveys
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [NO_CODE] (SAFE): This skill contains no executable scripts (Python, JavaScript, etc.). It is composed of Markdown documentation and a JSON metadata file. All logic is provided via natural language instructions for the LLM.
- [DATA_EXFILTRATION] (SAFE): No patterns for file system access or network operations (curl, wget, fetch) were detected. The skill operates entirely within the agent's chat context.
- [CREDENTIALS_UNSAFE] (SAFE): No hardcoded API keys, tokens, or secrets were found in the provided files.
- [REMOTE_CODE_EXECUTION] (SAFE): There are no package managers (npm, pip) or remote script downloads present in the skill's definition.
- [PROMPT_INJECTION] (SAFE): The instructions do not contain attempts to bypass safety filters, extract system prompts, or override agent behavior. The language is professional and task-oriented.
- [INDIRECT_PROMPT_INJECTION] (SAFE): While the skill ingests user input regarding survey goals, it lacks any high-risk capabilities (like shell access or network requests) that could be exploited via malicious data injection. The output is limited to generating Markdown survey plans.
Audit Metadata