pp-jalan
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides installation instructions for jalan-pp-cli using npx from the @mvanhorn/printing-press-library NPM package and go install from github.com/mvanhorn/printing-press-library. These resources originate from the vendor's own infrastructure.
- [REMOTE_CODE_EXECUTION]: The installation instructions for the CLI tool involve downloading and executing code from the author's NPM and GitHub repositories.
- [COMMAND_EXECUTION]: The skill instructs the agent to run various shell commands using the jalan-pp-cli binary to search, compare, and inspect accommodation data.
- [DYNAMIC_EXECUTION]: The skill includes instructions to compile the CLI binary from source using go build when running from a source checkout.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external accommodation data from Jalan which presents a potential surface for indirect prompt injection. 1. Ingestion points: Data retrieved from Jalan via the stay search, stay plan, and stay property commands. 2. Boundary markers: None explicitly defined in the provided instructions. 3. Capability inventory: The agent is authorized to use the Read Bash tool to execute CLI commands. 4. Sanitization: No specific sanitization logic is detailed for the processed external data.
Audit Metadata