pp-hotel-tonight

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the hotel-tonight-pp-cli and hotel-tonight-pp-mcp binaries from the vendor's GitHub repository using go install and an NPM package via npx.
  • [COMMAND_EXECUTION]: The skill's primary purpose is to execute shell commands using the hotel-tonight-pp-cli tool to perform searches and analysis.
  • [DATA_EXFILTRATION]: The CLI tool includes a --deliver webhook:<url> flag that allows the agent to route command output to an arbitrary external URL via an HTTP POST request.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the HotelTonight API, creating a surface for indirect prompt injection.
  • Ingestion points: Data returned by the inventory, watch, markets, and daily-drop subcommands in SKILL.md.
  • Boundary markers: The instructions do not specify any delimiters or warnings to the agent to distinguish between its own instructions and the data retrieved from the API.
  • Capability inventory: The skill possesses Read Bash capabilities and can write data to the filesystem or external webhooks via the --deliver flag.
  • Sanitization: There is no evidence of sanitization or strict schema validation for the external API data described in the skill documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 06:38 PM