openrouter-usage-analytics

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the OpenRouter API to track costs and usage metrics. This creates an interface where externally sourced data enters the agent's context.
  • Ingestion points: Data is fetched from https://openrouter.ai/api/v1/generation and https://openrouter.ai/api/v1/auth/key within SKILL.md.
  • Boundary markers: There are no explicit instructions or delimiters used to separate API response data from the rest of the agent's prompt context.
  • Capability inventory: The skill possesses the ability to execute shell commands via Bash (Python, curl, jq) and write files, as specified in the allowed-tools frontmatter.
  • Sanitization: The skill parses JSON responses and extracts specific fields without broad sanitization of the content before it is processed or logged.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:45 AM
Security Audit — agent-trust-hub — openrouter-usage-analytics