celery-expert
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides legitimate templates and guidelines for Celery development. It explicitly warns against security pitfalls like the use of 'pickle' serialization.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted task data but provides mitigation strategies.
- Ingestion points: Task arguments in
process_orderandcall_external_apiinSKILL.md. - Boundary markers: Delimiters are not used, but structural separation in code is present.
- Capability inventory: Includes database access (SQLAlchemy) and network requests (Requests) as shown in
SKILL.md. - Sanitization: Recommends Pydantic for input validation and schema enforcement.
Audit Metadata