content-humanizer

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFENO_CODEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [NO_CODE] (SAFE): The skill contains only documentation files (.md) and no executable scripts, binaries, or configuration files that trigger automated actions.
  • [EXTERNAL_DOWNLOADS] (LOW): The SKILL.md file recommends the installation of a secondary skill using 'npx skills add oakoss/agent-skills'. This involves downloading and executing content from an untrusted third-party GitHub account (oakoss) not included in the trusted organizations list.
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection as it is designed to ingest and process untrusted AI-generated prose. 1. Ingestion points: User-provided prose files or text segments described in SKILL.md. 2. Boundary markers: Absent; instructions do not specify the use of delimiters for input text. 3. Capability inventory: The skill relies on natural language rewriting and generation capabilities. 4. Sanitization: Absent; there are no instructions for the agent to sanitize or ignore instructions embedded within the user-provided prose.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 05:12 AM