pp-calendly

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user or agent to download and install the calendly-pp-cli and calendly-pp-mcp tools using npx (from @mvanhorn/printing-press-library) and go install (from github.com/mvanhorn/printing-press-library). These resources are managed by the vendor mvanhorn.- [DATA_EXFILTRATION]: The CLI tool supports a --deliver flag with a webhook:<url> sink, which can be used to transmit data retrieved from the Calendly API (such as organization memberships, user details, and scheduled events) to arbitrary external URLs.- [COMMAND_EXECUTION]: The skill requires the execution of the calendly-pp-cli binary to perform its primary functions.- [PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface where untrusted user input is passed to CLI commands.
  • Ingestion points: User-provided queries are passed to calendly-pp-cli which and feedback text is passed to calendly-pp-cli feedback (SKILL.md).
  • Boundary markers: There are no markers or instructions to delimit untrusted input from system commands.
  • Capability inventory: The CLI has the ability to execute shell commands, write to the local file system (file:<path>), and make network POST requests via webhooks.
  • Sanitization: No input validation or escaping mechanisms are described in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 08:21 AM
Security Audit — agent-trust-hub — pp-calendly