dev-event-kickoff
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as an entry point and router for an event-organizer skill collection. It primarily performs analysis of local project metadata (e.g.,
event-context.md, git logs, and file inventories) to provide routing recommendations to the user. No malicious patterns, such as prompt injection, data exfiltration, or unauthorized command execution, were identified. The skill also includes explicit safety instructions to exclude personal data and sensitive contract terms from persistent memory. - [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it ingests untrusted data from the local environment, including git history and project artifacts. However, the risk is negligible as the skill lacks capabilities to execute arbitrary commands, perform network operations, or evaluate dynamic code based on the ingested data.
- Ingestion points:
event-context.md, git log history, and local project files (e.g., budget spreadsheets, venue contracts). - Boundary markers: No explicit delimiters or 'ignore' instructions for external content are defined.
- Capability inventory: The skill does not use subprocesses, network tools (like curl/wget), or dynamic execution functions (like eval/exec).
- Sanitization: No explicit sanitization or validation of the ingested file content is described.
Audit Metadata