ts-chat
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected. The skill is intentionally designed to limit the agent's capabilities to non-destructive actions.
- [COMMAND_EXECUTION]: The skill permits the execution of inspection commands and tests. This is handled securely by instructing the agent to prefer read-only commands and to explicitly ask for user permission before running any command that might change the environment's state.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it can read local files and perform web searches.
- Ingestion points: Local filesystem and web search results (referenced in SKILL.md).
- Boundary markers: Absent.
- Capability inventory: Execution of inspection commands and tests (referenced in SKILL.md).
- Sanitization: Absent.
Audit Metadata