discord-manage-channel

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes curl commands to interact with the Discord API v10. This is the primary intended functionality of the skill and is directed at a well-known service domain (discord.com).
  • [DATA_EXFILTRATION]: Authentication is managed through the DISCORD_BOT_TOKEN environment variable, which is a standard and secure practice for managing bot credentials without hardcoding them.
  • [PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection as it ingests user-provided data for channel names and topics.
  • Ingestion points: User requests for name, topic, and permission_overwrites processed in SKILL.md.
  • Boundary markers: Absent.
  • Capability inventory: Execution of curl requests to external API endpoints (SKILL.md, examples.md).
  • Sanitization: Includes length and character set validation rules in SKILL.md, though it does not explicitly filter for embedded instructions.
  • [SAFE]: The skill explicitly instructs the agent to require human confirmation before performing destructive operations like channel deletion, which mitigates the risk of accidental data loss.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 12:32 PM