prompt-optimizer

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by processing untrusted user data to generate instructions for downstream tasks.
  • Ingestion points: Untrusted user requests are ingested whenever the skill is activated by vague language or optimization triggers as described in SKILL.md.
  • Boundary markers: The prompt templates in SKILL.md for generating the final optimized output do not utilize delimiters or specific instructions to isolate or ignore embedded user commands.
  • Capability inventory: The skill is restricted to the AskUserQuestion tool and does not have permissions for file access, network requests, or direct code execution.
  • Sanitization: There is no evidence of input filtering or escaping for user-provided content before it is included in the output prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 01:11 PM