Psychologist
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze user-supplied text such as character descriptions and behavioral scenarios, which establishes an ingestion surface for untrusted data.\n
- Ingestion points: User-provided character details, interaction history, and behavioral scenarios analyzed during the skill's workflow (SKILL.md).\n
- Boundary markers: The instructions do not define explicit delimiters or warnings to ignore embedded instructions within user data.\n
- Capability inventory: The skill is limited to textual analysis and output; it contains no file system access, network capabilities, or code execution tools.\n
- Sanitization: No content sanitization or validation logic is specified in the skill.\n- [SAFE]: The skill functions as a specialized persona for psychological character studies. It does not attempt to exfiltrate data, bypass safety filters, or execute unauthorized commands. No evidence of obfuscation or malicious metadata was found.
Audit Metadata