slack

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external Slack channels and possesses capabilities to interact with those channels.\n
  • Ingestion points: External content is ingested through the readMessages, reactions, and listPins actions defined in SKILL.md.\n
  • Boundary markers: No specific boundary markers or instructions to disregard potential commands within the ingested data were found.\n
  • Capability inventory: The skill possesses significant capabilities including sendMessage, editMessage, deleteMessage, pinMessage, unpinMessage, and react.\n
  • Sanitization: No explicit evidence of sanitization or validation of the ingested Slack content is provided in the skill files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 07:40 AM