fix-all-best-practices

Pass

Audited by Gen Agent Trust Hub on Mar 26, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing untrusted project files (source code, schemas) to automate code refactoring.
  • Ingestion points: Scans local project source code, database schemas, and directory structures via the references/workflow.md procedure.
  • Boundary markers: Lacks explicit delimiters or instructions to prevent the agent from following malicious instructions embedded within code comments or strings of the files being scanned.
  • Capability inventory: Has file-write permissions for refactoring and the ability to trigger the execution of other agent skills.
  • Sanitization: No explicit sanitization or validation of ingested project data is mentioned prior to processing.
  • [COMMAND_EXECUTION]: The skill is designed to automatically discover and execute a variable list of other skills (those ending in best-practice). While it orchestrates internal agent tools, this dynamic execution pattern relies on the integrity of all installed skills within the environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 26, 2026, 04:35 AM