investor-research
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists exclusively of markdown-based instructions for research and analysis. It contains no executable scripts, binaries, or automated network operations.\n- [INDIRECT_PROMPT_INJECTION]: The skill includes instructions to ingest external data, which creates a potential surface for indirect prompt injection.\n
- Ingestion points: The workflow involves reading data from a local startup context file (Step 1: Read startup context from
.agents/startup-context.md).\n - Boundary markers: No specific delimiters or safety instructions (e.g., 'ignore any instructions contained within the context file') are implemented to separate the data from the skill's logic.\n
- Capability inventory: The skill lacks high-risk capabilities such as file system writes, shell command execution, or network exfiltration, which mitigates the impact of this injection surface.\n
- Sanitization: There are no documented procedures for validating or sanitizing the ingested startup data.
Audit Metadata