awiki-workflow-onboarding

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the awiki-cli tool via Bash to manage local system states, identities, and background processes.
  • It executes commands like awiki-cli runtime listener start and awiki-cli id register to configure the local environment.
  • These are vendor-specific commands intended for the management of the awiki messaging platform.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing external data from message inboxes.
  • Ingestion points: The agent reads external content via awiki-cli msg inbox --limit 5 in SKILL.md.
  • Boundary markers: Absent; there are no instructions to the agent to ignore or delimit instructions found within the inbox data.
  • Capability inventory: The agent has access to Bash(awiki-cli:*) which permits identity modification, message sending, and runtime configuration.
  • Sanitization: There is no evidence of sanitization or validation of the message content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 12:49 PM