pp-wavespeed

Pass

Audited by Gen Agent Trust Hub on Jul 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches and installs the wavespeed-pp-cli and wavespeed-pp-mcp tools from the developer's GitHub repository and the @mvanhorn NPM registry during setup.
  • [COMMAND_EXECUTION]: Executes the local wavespeed-pp-cli binary to perform API interactions, manage local database records, and handle brand profiles.
  • [DATA_EXFILTRATION]: Features an output delivery system (--deliver webhook:<url>) that allows the CLI to POST command results, which may contain sensitive billing or account data, to external URLs.
  • [PROMPT_INJECTION]:
  • Ingestion points: Data is ingested from untrusted sources via the --prompt, --input, --input-file, --from (CSV/JSON), and feedback --stdin parameters.
  • Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands within processed data, creating a surface for indirect prompt injection.
  • Capability inventory: The skill has network access (API and webhooks), file system access (for local storage and sinks), and database interaction capabilities.
  • Sanitization: There is no evidence of input validation or escaping for data being passed into the model runs or the natural language query tool (which).
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 12, 2026, 08:09 AM
Security Audit — agent-trust-hub — pp-wavespeed