hitl-approval

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted human feedback from Slack, creating an indirect prompt injection surface.\n
  • Ingestion points: User data enters via the Slack interactions webhook in apps/slack/app/api/slack/interactions/route.ts.\n
  • Boundary markers: There are no markers or instructions defined to prevent the agent from interpreting feedback as new commands.\n
  • Capability inventory: The agent has access to several high-privilege tools, including Bash, Write, and Edit.\n
  • Sanitization: The skill performs signature verification to authenticate Slack as the source, but does not sanitize the content for prompt-based attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 10:33 PM