search
Fail
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: HIGHPRIVILEGE_ESCALATIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PRIVILEGE_ESCALATION]: The skill explicitly instructs the agent to bypass sandbox security by default, stating that commands should be run outside the sandbox on the first attempt. It further directs the agent to request escalated permissions ("sandbox_permissions: 'require_escalated'") specifically to access the user's local credentials.
- [COMMAND_EXECUTION]: The skill's primary functionality relies on executing shell commands through the 'entire' CLI tool to perform searches and explain checkpoints.
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes untrusted data from repository content and session transcripts, which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Content retrieved via 'entire search' and 'entire checkpoint explain' (SKILL.md).
- Boundary markers: No delimiters or instructions are provided to the agent to treat external content as untrusted data.
- Capability inventory: Shell command execution capabilities used to interact with the 'entire' CLI (SKILL.md).
- Sanitization: There is no evidence of sanitization or validation of the data retrieved from external sources before it is interpreted by the agent.
Recommendations
- AI detected serious security threats
Audit Metadata