Skills
Navigate
skills/jr2804/prompts/3gpp-portal-authentication/Gen Agent Trust Hub

3gpp-portal-authentication

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches and parses HTML metadata from the 3GPP portal, creating a vulnerability surface for instructions embedded in external content.
  • Ingestion points: The get_tdoc_metadata function in SKILL.md uses BeautifulSoup to parse HTML from portal.3gpp.org.
  • Boundary markers: No delimiters or safety instructions are used to separate external data from agent instructions.
  • Capability inventory: The skill uses the requests library for network communication but does not show file writing or command execution capabilities.
  • Sanitization: The fetched content is parsed directly without sanitization or validation of the input fields.
  • [PROMPT_INJECTION]: The skill provides code patterns that contain a logical flaw in authentication handling. The authenticate method raises an error when login is successful and proceeds when it fails, effectively instructing the agent to bypass authentication verification.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 02:34 AM