fancy-orient

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a bundled Python script (scripts/hunt.py) to conduct market research. This script is used to fetch and parse Bing search results locally, providing the agent with evidence of user pain points and competitor weaknesses.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests and processes untrusted data from the web. \n
  • Ingestion points: The agent ingests search result titles and snippets returned from Bing via the hunt.py script.\n
  • Boundary markers: The instructions do not define specific delimiters for these snippets, though the agent is directed to quote the results to the user.\n
  • Capability inventory: The agent has the capability to execute the local search script and write a proposal.md file to the current directory.\n
  • Sanitization: There is no explicit sanitization or filtering of the external search content before it is incorporated into the product proposal.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 09:55 AM