recoup-research-playlist-targets

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill documentation provides specific curl command templates for the agent to interact with the Recoupable API. This is the intended mechanism for data retrieval within the skill's scope.
  • [EXTERNAL_DOWNLOADS]: Fetches artist profile, metrics, and audience data from the vendor's official API at api.recoupable.com. This is considered safe as it utilizes the author's own infrastructure.
  • [PROMPT_INJECTION]: The skill ingests data from external sources via web search and deep research endpoints (/research/web, /research/deep). While this creates a surface for indirect prompt injection, it is central to the skill's research purpose.
  • Ingestion points: references/workflows.md (via /research/web, /research/deep, and /research/insights).
  • Boundary markers: None explicitly defined in the prompt templates.
  • Capability inventory: Shell execution (via curl), file system writing (to the research/ directory), and drafting of outreach communications.
  • Sanitization: No explicit sanitization logic for ingested data is provided in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 03:07 AM