skills/mnhkahn/cyeam-cli/phonetic/Gen Agent Trust Hub

phonetic

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the cyeam command-line utility to perform phonetic lookups. The user-supplied word is passed as an argument to this command.- [EXTERNAL_DOWNLOADS]: The skill fetches content from the Youdao Dictionary webpage to retrieve phonetic information and definitions.- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting untrusted data from an external source.
  • Ingestion points: User input via the word argument and external dictionary data fetched from the Youdao website (SKILL.md).
  • Boundary markers: No specific delimiters or warnings to ignore embedded instructions are present in the skill definition.
  • Capability inventory: The skill is capable of executing shell commands using the cyeam tool.
  • Sanitization: There is no explicit evidence of sanitization for the word input or the data retrieved from the dictionary website before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 12:29 AM
Security Audit — agent-trust-hub — phonetic