pp-placeit

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the placeit-pp-cli binary using npx and go install from the developer's official accounts on NPM (@mvanhorn) and GitHub (github.com/mvanhorn).
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to install the binary, verify the installation environment, and run the catalog search and analysis tools.
  • [DATA_EXFILTRATION]: The CLI tool supports a --deliver webhook:<url> feature that allows the transmission of command outputs—including sensitive account status or bookmarked templates—to arbitrary remote URLs.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes template metadata (names, descriptions, tags) from an external, third-party catalog (Placeit).
  • Ingestion points: Placeit template catalog data retrieved during sync and search operations in SKILL.md.
  • Boundary markers: The skill uses a JSON response envelope for machine readability.
  • Capability inventory: The skill environment allows file reads and shell command execution.
  • Sanitization: There is no evidence of sanitization or filtering of the external catalog content before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 09:18 AM
Security Audit — agent-trust-hub — pp-placeit