aeon-huggingface-trending

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses curl commands to retrieve JSON data from Hugging Face's trending endpoints for models, datasets, and spaces.\n- [EXTERNAL_DOWNLOADS]: Fetches metadata and documentation from Hugging Face, a well-known service in the AI community, to provide daily updates.\n- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it processes and summarizes untrusted text from external model cards and README files.\n
  • Ingestion points: Remote content fetched from Hugging Face repository metadata (SKILL.md).\n
  • Boundary markers: Absent; no specific delimiters are used to separate external content from the agent's instructions.\n
  • Capability inventory: Shell access for data retrieval via curl and text analysis capabilities (SKILL.md).\n
  • Sanitization: Absent; there is no mention of filtering or escaping logic for the retrieved external text.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 01:11 PM
Security Audit — agent-trust-hub — aeon-huggingface-trending