tinyfish-doctor

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the @tiny-fish/cli tool from the npm registry using npx. This ensures the latest diagnostic logic is used. The package is a resource provided by the skill's author.
  • [COMMAND_EXECUTION]: Executes repair commands identified by the diagnostic tool. The skill follows a strict protocol for these executions, respecting exit codes and safety flags (unattended_safe) to prevent unauthorized or dangerous configuration changes.
  • [INDIRECT_PROMPT_INJECTION]: Ingests structured JSON data from the CLI tool's output. The skill mitigates risks associated with processing this data by validating schema versions and using authored messages rather than raw system output for reporting.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 07:08 PM
Security Audit — agent-trust-hub — tinyfish-doctor