create-artist

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands (curl, jq, grep) to perform a series of 8 sequential API calls and manage a local checklist file (RECOUP.md). These operations are scoped to the vendor's API and the artist's workspace directory.
  • [EXTERNAL_DOWNLOADS]: Performs multiple data retrieval operations from api.recoupable.com, fetching artist profiles, career data, and web search results. This behavior is documented and aligns with the skill's enrichment purpose.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its ingestion of untrusted external data.
  • Ingestion points: Web search results (/api/research/web) and artist profile bios (/api/research/profile) are pulled into the agent's context in Step 4.
  • Boundary markers: No explicit delimiters are used when synthesizing external data into the final knowledge base report in Step 8.
  • Capability inventory: The skill possesses file-write capabilities to the local workspace (RECOUP.md and the releases/ directory) and network access to the Recoup API.
  • Sanitization: There is no specified logic for validating or escaping external content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 09:47 PM
Security Audit — agent-trust-hub — create-artist