model-registry-manager
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon user requests related to ML deployment, which creates an attack surface for instructions embedded in user data.\n
- Ingestion points: User prompts mentioning "model registry manager" or related MLOps topics as defined in
SKILL.md.\n - Boundary markers: The skill lacks explicit markers or instructions in
SKILL.mdto treat user-provided data as untrusted or to ignore embedded commands.\n - Capability inventory: The frontmatter in
SKILL.mdindicates access toBash,Read,Write,Edit, andGreptools.\n - Sanitization: No sanitization or validation logic is defined in
SKILL.mdfor processing external or user-provided content.
Audit Metadata