event-definition
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists exclusively of instructional Markdown reference guides and quality checklists. No executable scripts, network requests, or sensitive file access patterns were identified within the skill body or references.\n- [INDIRECT_PROMPT_INJECTION]: The skill has a theoretical attack surface for indirect prompt injection as it processes user-provided event definitions.\n
- Ingestion points: User-supplied event definitions (SKILL.md).\n
- Boundary markers: Absent; the instructions do not specify delimiters for untrusted user input.\n
- Capability inventory: Access to Bash, Write, Read, and AskUserQuestion tools is defined in the frontmatter, though the skill contains no logic to invoke Bash automatically.\n
- Sanitization: No explicit sanitization or filtering of input data is performed.\n
- Assessment: The risk is minimal as the instructions focus strictly on architectural review (e.g., checking for past tense and domain language), which guides the agent to treat the input as data to be evaluated against rules rather than instructions to be executed.
Audit Metadata