creator-registry
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from external sources, creating a potential surface for indirect prompt injection. However, it includes explicit defensive instructions to mitigate this risk.
- Ingestion points: The skill reads from
memory/creators/candidates.mdand processes user-pasted content from CRM or spreadsheet exports. - Boundary markers: Instruction 3 explicitly directs the agent to treat all pasted or exported data as untrusted and to ignore any embedded directives that might attempt to override its behavior.
- Capability inventory: The skill is authorized to read and write within the
memory/directory to maintain creator records. It does not perform network operations or execute shell commands. - Sanitization: The skill employs clear instructional constraints to ensure the agent processes data purely as information rather than executable instructions.
Audit Metadata