Creator Partnership Manager

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE] (SAFE): The analyzed skill consists solely of a markdown file (SKILL.md) providing a workflow template.
  • Evidence: No external scripts (.py, .js, .sh) or configuration files for automated tools are included.
  • [PROMPT_INJECTION] (SAFE): No patterns of instruction overriding, safety filter bypasses, or system prompt extraction attempts were detected in the instructional text.
  • [DATA_EXFILTRATION] (SAFE): The skill contains no commands or scripts that access sensitive files (~/.ssh, .env, etc.) or perform network operations (curl, wget).
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill identifies a workflow for managing influencer contracts and collaborations, which involves processing external data.
  • Ingestion points: Creator contracts and partnership communications (implied by the skill's purpose).
  • Boundary markers: Absent; there are no instructions to the agent on how to separate untrusted data from instructions.
  • Capability inventory: None; the skill does not define any subprocess calls, file writes, or network operations.
  • Sanitization: Absent; no logic is provided to clean or validate ingested documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:36 PM