close
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the forge close CLI command to transition issues to a closed state.
- [INDIRECT_PROMPT_INJECTION]: The skill accepts issue identifiers from the user which are interpolated into a shell command, creating a potential surface for argument or command injection if not handled correctly by the agent. * Ingestion points: Issue identifiers () provided to the forge close command in SKILL.md. * Boundary markers: None present. * Capability inventory: Command execution via the forge CLI tool. * Sanitization: The skill does not define specific input validation or sanitization routines for the identifiers.
Audit Metadata