pp-extron

Warn

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands for installation and operation, including npx, go install, and multiple subcommands of the extron-pp-cli binary.
  • [EXTERNAL_DOWNLOADS]: Fetches and installs the CLI tool and its dependencies from the vendor's resources on GitHub (github.com/mvanhorn/printing-press-library) and NPM (@mvanhorn/printing-press-library). These are documented as vendor-owned resources and do not escalate the verdict.
  • [DATA_EXFILTRATION]: The extron-pp-cli includes a --deliver webhook:<url> feature that enables POSTing command output to arbitrary external URLs. Furthermore, the feedback command can be configured to automatically transmit local data to a remote endpoint via EXTRON_FEEDBACK_ENDPOINT.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, posing a risk of indirect prompt injection.
  • Ingestion points: Processes user-supplied CSV files (--bom ./rack.csv) and fetches documentation from the Extron website.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious instructions embedded in the documents or CSV data.
  • Capability inventory: The skill allows for command execution, file system writes (--dir ./docs), and network requests (--deliver webhook).
  • Sanitization: The instructions do not specify any validation or sanitization of the content before it is processed by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 16, 2026, 03:44 PM
Security Audit — agent-trust-hub — pp-extron