text-optimizer

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted user-provided files which presents a surface for indirect prompt injection. A malicious instruction within a target file could attempt to influence the agent behavior during the analysis or editing phase.
  • Ingestion points: Reads user-specified target files in SKILL.md via Read, Grep, and Glob tools.
  • Boundary markers: The skill does not use boundary markers for the data it ingests, although it recommends adding XML tags to generated output.
  • Capability inventory: The skill utilizes Write and Edit tools to modify files.
  • Sanitization: No specific sanitization of external content is performed.
  • [COMMAND_EXECUTION]: The skill uses standard file system tools to manipulate text files. These tools are used legitimately for the skill's stated purpose.
  • [SAFE]: No malicious code, obfuscation, or unauthorized network activity was detected. All external references target the author's verified vendor resources and are documented neutrally.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 09:22 PM