skill-composer-studio

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill allows users to define custom multi-step workflows by mapping descriptions to sequences of existing skills, creating a potential surface for indirect instructions.
  • Ingestion points: User-provided workflow descriptions processed in SKILL.md.
  • Boundary markers: Absent. No delimiters are specified to separate user-provided workflow logic from the agent's core instructions.
  • Capability inventory: The skill orchestrates other agent skills and transformations, potentially inheriting the capabilities of any chained skill in the catalog.
  • Sanitization: Absent. The skill lacks explicit sanitization or validation of the logic provided in the user's workflow description.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:02 PM
Security Audit — agent-trust-hub — skill-composer-studio