language-audit

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local script named language-router.py to perform translation quality scoring. This represents local code execution which is an intended part of the skill logic.
  • [EXTERNAL_DOWNLOADS]: The skill fetches and parses HTML content and hreflang annotations from external URLs provided by the user to perform the audit.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. 1. Ingestion points: It ingests untrusted data from external URLs (HTML source, hreflang tags, and page content) and content assets provided by the user. 2. Boundary markers: There are no explicit instructions to the agent to treat this external content as untrusted or to ignore instructions embedded within it. 3. Capability inventory: The agent has the capability to execute local commands via the language-router.py script. 4. Sanitization: No sanitization or validation of the fetched external content is described, creating a risk that malicious instructions in the audited content could influence the agent's output or actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 01:02 PM