tinyfish

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to scrape and extract data from external, untrusted websites using natural language goals.
  • Ingestion points: The extract.py script and SKILL.md code examples ingest data from user-specified URLs via the mino.ai API.
  • Boundary markers: None identified. The skill does not explicitly instruct the agent to ignore instructions embedded within the scraped content.
  • Capability inventory: The skill has network access to mino.ai and can write the extracted JSON results to standard output, which the agent then processes.
  • Sanitization: None identified. The raw output from the external extraction service is parsed and returned directly to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 05:33 AM
Security Audit — agent-trust-hub — tinyfish