prompt-optimizer

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill consists entirely of natural language instructions in SKILL.md and does not include any scripts, binaries, or configuration files that execute code.
  • [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user input (draft prompts) without explicit boundary markers or sanitization logic. While this creates a surface for indirect prompt injection, the risk is minimal as the skill lacks capabilities like network access or file system modification.
  • Ingestion points: User prompts provided to the optimizer as described in SKILL.md.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined for the user input.
  • Capability inventory: The skill does not request any tools, network access, or file system permissions in its configuration.
  • Sanitization: There is no logic provided to sanitize or filter the content of the user's draft prompt before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 08:36 AM