qqbot-channel

Pass

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection through external data processed from the QQ Open Platform API.
  • Ingestion points: The skill ingests untrusted data from the API, including guild names, channel descriptions, member nicknames, and forum thread content as documented in SKILL.md and references/api_references.md.
  • Boundary markers: There are no boundary markers or delimiters defined in the instructions to help the agent differentiate between data retrieved from the API and the agent's core instructions.
  • Capability inventory: The skill is equipped with high-impact capabilities, such as the ability to delete subchannels, delete all announcements, and publish forum posts via the qqbot_channel_api tool.
  • Sanitization: No sanitization, validation, or escaping of the content retrieved from the external API is specified before the agent processes or displays the data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 07:05 PM