diamond-sutra
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the way it processes user input.
- Ingestion points: Untrusted user input is ingested through the
[question-or-anxiety-context]argument defined inSKILL.md. - Boundary markers: The instructions do not use delimiters or boundary markers to isolate user-provided text from the skill's core logic and persona instructions.
- Capability inventory: The skill is configured with access to
Read,Write,Edit, andBashtools as specified in the YAML frontmatter ofSKILL.md. - Sanitization: The instructions contain no logic for sanitizing or validating user input before the agent acts upon it.
Audit Metadata