improve-skill

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill uses the opencode CLI and standard shell commands (ls, cat) to manage session data and skill files. These operations are limited to the application's own configuration directory (~/.config/opencode/).
  • [PROMPT_INJECTION] (SAFE): The skill manages untrusted data in the form of session transcripts. It implements mitigation by using XML-style boundary markers and instructing the user to perform the analysis in a fresh session, reducing the risk of the agent being misled by instructions embedded in the transcript.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:37 PM