slack-user-context

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting data from Slack history.
  • Ingestion points: The skill reads from Slack DM history (im:history) and public channel searches (search:read.public) as documented in SKILL.md.
  • Boundary markers: No boundary markers or 'ignore' instructions are present to prevent the agent from obeying instructions embedded in Slack messages.
  • Capability inventory: The skill integrates with pyATS and slack-network-alerts, which can perform network actions and communications.
  • Sanitization: The description does not mention any sanitization or validation of the external Slack content.
  • [NO_CODE]: The skill consists exclusively of the SKILL.md file and does not include any Python or JavaScript code files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 12:31 AM