opencode-skill-creation

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (mkdir -p, ln -s) to manage the filesystem structure and create symbolic links for skill discovery.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided workflow context to generate new skill files, which represents an ingestion surface for potentially malicious instructions.
  • Ingestion points: User requests and target workflow context used to populate the content of new SKILL.md files (SKILL.md).
  • Boundary markers: Absent. The skill does not specify delimiters or explicit warnings to the agent to ignore instructions embedded in the input data.
  • Capability inventory: Includes filesystem write access, directory creation, and symbolic link creation (SKILL.md).
  • Sanitization: Absent. There are no defined procedures for sanitizing or escaping user-provided text before it is written into the new skill files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 10:49 AM
Security Audit — agent-trust-hub — opencode-skill-creation