skills/workersio/skills/wio/Gen Agent Trust Hub

wio

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: No security issues were detected. The skill's author and internal resources are consistent with the provided vendor context and intended functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves analyzing project source code and test suites, which creates a surface for indirect prompt injection. This risk is assessed as safe due to the skill's design and mitigating controls.
  • Ingestion points: Repository source code, existing tests, and CI configuration files are read into the agent's context during 'scan', 'test', and 'doctor' workflows.
  • Boundary markers: The workflow enforces a multi-step review process with explicit verdicts (KEEP, REDO, REMOVE), ensuring main-agent or human oversight before any code changes are finalized.
  • Capability inventory: The skill can modify test files and execute repository-native shell commands for validation as documented in the reference guides.
  • Sanitization: The skill treats ingested content as data for analysis rather than authoritative instruction, and the emphasis on protecting 'meaningful behavior' over raw coverage acts as a functional safeguard against obeying malicious payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 04:54 PM
Security Audit — agent-trust-hub — wio