deep-research
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates the collection and processing of data from arbitrary external sources, which is then used as input for the agent's synthesis phase. This creates a surface for indirect prompt injection where malicious instructions in the source material could potentially influence the agent's behavior.
- Ingestion points: External research findings gathered by subagents from various market and competitive sources as described in
SKILL.md. - Boundary markers: The skill does not specify the use of delimiters or 'ignore' instructions to separate untrusted research data from the agent's internal reasoning or instructions.
- Capability inventory: The agent performs file system writes to
research/and thestartup/vault, and performs file system reads to generate the final synthesis. - Sanitization: No sanitization or validation of the ingested external content is mentioned or required by the workflow.
Audit Metadata