market-analysis

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the web and local research files, creating a potential surface for indirect prompt injection.\n
  • Ingestion points: Untrusted data enters the agent context through WebSearch and WebFetch tool outputs, as well as existing research evidence files located in tmp/research/.\n
  • Boundary markers: The skill lacks instructions to wrap external content in delimiters or to explicitly ignore embedded instructions within the research data, which could lead the agent to follow malicious commands hidden in web content.\n
  • Capability inventory: The skill has significant capabilities, including the ability to write to the file system (docs/ and .claude/ directories), perform network operations via research tools, and spawn subagents using spawn_agent.\n
  • Sanitization: No sanitization or validation steps are included to clean external data before it is written to the final output artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 10:12 AM