awiki-bundle

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines a command surface for the awiki-cli tool, allowing the agent to execute status, documentation, and configuration commands via the Bash tool as part of its routing functionality.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes and interprets output from the awiki-cli tool.
  • Ingestion points: Data returned from awiki-cli status, docs, and schema commands (SKILL.md).
  • Boundary markers: Not identified.
  • Capability inventory: Ability to execute shell commands via Bash(awiki-cli:*).
  • Sanitization: Not identified.
  • [SAFE]: No malicious patterns, such as direct prompt injection, data exfiltration, or obfuscation, were detected in the skill instructions or metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 12:49 PM
Security Audit — agent-trust-hub — awiki-bundle