stock-analyze
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [NO_CODE]: The provided files contain configuration and instructions but no executable source code or scripts.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest external data from news and sentiment sources, creating a potential surface for indirect prompt injection.
- Ingestion points: SKILL.md specifies the use of news and sentiment tools.
- Boundary markers: None present in the instructions to delimit or warn against instructions embedded in external content.
- Capability inventory: The skill utilizes technical analysis tools (get_quant_technical) and review protocol tools (get_review_protocol).
- Sanitization: No explicit sanitization or filtering instructions are provided for the external content.
Audit Metadata