pp-zameen

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the zameen-pp-cli tool using npx -y @mvanhorn/printing-press-library and go install github.com/mvanhorn/printing-press-library/.... These resources are hosted on the vendor's own infrastructure.
  • [COMMAND_EXECUTION]: The skill relies on the Bash tool to execute zameen-pp-cli for property searches, data mirroring, and market analysis.
  • [DATA_EXFILTRATION]: The tool includes a --deliver webhook:<url> feature that allows routing command output to any external URL provided by the user, which is a functional capability for data transport.
  • [PROMPT_INJECTION]: The skill ingests untrusted property listing data from Zameen.com search results. This represents an indirect prompt injection surface as the agent processes server-rendered content.
  • Ingestion points: Zameen.com search pages processed via listings and find commands (SKILL.md).
  • Boundary markers: The skill uses structured JSON output with a provenance envelope and allows the agent to --select specific fields, which helps limit the exposure of untrusted content.
  • Capability inventory: The skill has Read and Bash capabilities and can execute arbitrary CLI commands via the zameen-pp-cli binary.
  • Sanitization: The skill advises the agent to strip PII (names, emails, phones) before 'teaching' new patterns to the local learning loop.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 10:22 AM
Security Audit — agent-trust-hub — pp-zameen