skills/akhy/agent-skills/plurk-trend/Gen Agent Trust Hub

plurk-trend

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from Plurk, which could contain malicious instructions meant to influence the agent's behavior (Indirect Prompt Injection).
  • Ingestion points: The script scripts/plurk_trend.py fetches user-generated content directly from the Plurk API (https://www.plurk.com/APP/Timeline/getPlurks).
  • Boundary markers: The skill instructions lack delimiters or explicit warnings to the agent to ignore any embedded instructions within the fetched Plurk content.
  • Capability inventory: No dangerous capabilities such as file system access, arbitrary command execution, or dynamic code evaluation were identified within the skill's scripts.
  • Sanitization: The skill returns raw content (content_raw) and HTML content (content) from the API to the agent without sanitization or filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 11:10 AM