easy-opencode

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts arbitrary instructions or questions from users and interpolates them directly into a shell command template for execution.
  • Ingestion points: User input strings are placed into the '[instructions/questions]' placeholder in the SKILL.md command templates.
  • Boundary markers: The command template uses double quotes around the input string but lacks explicit delimiters or instructions to ignore embedded commands.
  • Capability inventory: The skill executes the 'opencode' binary which has the capability to plan and implement code changes within the repository.
  • Sanitization: There is no evidence of escaping or validation of the user input before it is passed to the shell.
  • [COMMAND_EXECUTION]: The skill relies on the execution of a non-standard external binary 'opencode' (declared in the metadata) to perform its core functions. It executes this tool via the shell using the 'opencode run' command.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 11:31 PM
Security Audit — agent-trust-hub — easy-opencode