influencer-partnerships
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data regarding creator content and audience engagement, which is an ingestion surface for untrusted information. However, the skill lacks any capabilities to execute code, write files, or perform network operations, which mitigates the risk. * Ingestion points: Step 2 involves analyzing creator work and conversation history. * Boundary markers: The skill instructs the agent to rely only on operator-supplied or verified evidence. * Capability inventory: No tools or scripts are defined. * Sanitization: None.
- [SAFE]: This skill consists solely of natural language instructions and does not contain any executable scripts, dependencies, or command-line patterns.
Audit Metadata