autoconsultant

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as a workflow manager that ingests and processes external data, establishing an indirect prompt injection surface.
  • Ingestion points: The skill processes content from the target repository, plan.md files, and user responses during the consultation phase as described in SKILL.md.
  • Boundary markers: It implements robust encapsulation for handoff payloads using unambiguous start/end markers and dynamic backtick fencing to preserve data integrity.
  • Capability inventory: The skill explicitly restricts itself from performing Git mutations, repository writes, or executing child processes, limiting the potential impact of an injection.
  • Sanitization: It includes a verification step to ensure handoff payloads are byte-for-byte identical to approved sources before completion.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 04:56 PM
Security Audit — agent-trust-hub — autoconsultant