drug-co-il-lookup

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a search and fetch mechanism for drug information from the official Israeli Pharmacists Organization website (drug.co.il).
  • [EXTERNAL_DOWNLOADS]: The script performs network requests using the requests library to drug.co.il and provides links to official patient leaflets hosted on the Israeli Ministry of Health domain (mohpublic.z6.web.core.windows.net). These are trusted and well-known sources for the skill's purpose.
  • [COMMAND_EXECUTION]: The skill uses a Python script (lookup.py) to perform its tasks. The script uses requests and BeautifulSoup for data retrieval and parsing. No unsafe shell command execution or privilege escalation was detected.
  • [DATA_EXFILTRATION]: No sensitive local data access or external transmission to unauthorized domains was detected. The network traffic is limited to the target site and the search query provided by the user.
  • [PROMPT_INJECTION]: The skill instructions do not contain attempts to override agent behavior or bypass safety guidelines. Natural instructional language is used to guide the agent on how to use the tool and interpret results.
  • [INDIRECT_PROMPT_INJECTION]: While the skill processes external data (HTML from drug.co.il), it primarily parses it into structured JSON. The raw_text field is provided as a fallback. The risk is minimal as the source is a reputable organizational site and the output is used to answer user queries about medication in a clinical/informational context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 08:02 AM
Security Audit — agent-trust-hub — drug-co-il-lookup