pp-usgs-earthquakes

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions direct users to install the usgs-earthquakes-pp-cli and usgs-earthquakes-pp-mcp binaries from the author's repository using npx and go install (e.g., github.com/mvanhorn/printing-press-library).
  • [COMMAND_EXECUTION]: The watch command includes a --notify flag that allows the execution of arbitrary shell commands as hooks. The sql command enables running direct SQL queries against a local SQLite database.
  • [DATA_EXFILTRATION]: The --deliver flag supports a webhook:<url> sink, which allows the agent to send command outputs and earthquake data to external network endpoints via HTTP POST requests.
  • [PROMPT_INJECTION]: The skill ingests data from external USGS feeds, creating an attack surface for indirect prompt injection. While USGS is a trusted source, the skill's capabilities (shell hooks, SQL, webhooks) could be exploited if malicious data were introduced into the feed.
  • Ingestion points: USGS FDSN Event service and summary feeds.
  • Boundary markers: None specified in instructions.
  • Capability inventory: Shell command execution via --notify, SQL execution via sql command, and network exfiltration via --deliver webhook.
  • Sanitization: No explicit sanitization or validation of the external feed content is documented before it is used in the monitoring hooks or processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 06:33 PM
Security Audit — agent-trust-hub — pp-usgs-earthquakes