event-format-selection
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides a decision-making framework for event formats based on recognized industry precedents like DevOpsDays and Strange Loop. No malicious command execution, data exfiltration, or prompt injection patterns were found. All referenced URLs are informational links to legitimate academic or community sources.
- [NO_CODE]: The skill does not include any scripts, binaries, or package installation commands. It operates purely as an instructional layer for an AI agent.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface through its strategy interview process.
- Ingestion points: User responses to the 11-question structural interview in SKILL.md.
- Boundary markers: None; the instructions do not implement specific delimiters or 'ignore' directives for user-provided data.
- Capability inventory: Limited to text-based recommendations and delegation to other modular skills in the samber/dev-event-organizer-skills collection. It lacks the ability to write to the filesystem, perform network operations, or execute subprocesses.
- Sanitization: No validation or filtering is performed on user inputs before they are used to generate recommendations.
Audit Metadata