skills/ravi-hq/deepthink-skills/think/Gen Agent Trust Hub

think

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted input that can lead to indirect prompt injection (Category 8).
  • Ingestion points: Data enters the context via the $ARGUMENTS variable and the WebFetch tool.
  • Boundary markers: The lead agent's restatement of the situation acts as a non-technical boundary before data is passed to sub-agents.
  • Capability inventory: The skill can write files (Write), search/fetch the web (WebSearch, WebFetch), and orchestrate teams of agents (Agent, TeamCreate).
  • Sanitization: There is no programmatic sanitization or escaping of the ingested data before it is used in prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 11:52 PM