travel-hotel-research

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of ingesting untrusted data from external sources.
  • Ingestion points: The skill fetches external travel data, including hotel reviews, attraction descriptions, and listing details, from the Crawlora API (api.crawlora.net) as documented in SKILL.md and reference/endpoints.md.
  • Boundary markers: There are no explicit instructions or delimiters defined to separate external data from system instructions, increasing the risk that embedded instructions in reviews could influence the agent.
  • Capability inventory: The skill uses scripts/crawlora.sh to perform network requests via curl to fetch and return data for agent processing.
  • Sanitization: No explicit sanitization or filtering logic is mentioned for the data retrieved from external travel platforms.
  • [COMMAND_EXECUTION]: The skill uses a local shell script to interface with the vendor's API.
  • Evidence: The script scripts/crawlora.sh executes curl to communicate with api.crawlora.net. It uses safe parameter handling (URL encoding for GET requests) and is a standard component for the skill's intended travel research purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 06:10 PM
Security Audit — agent-trust-hub — travel-hotel-research