market-researcher
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (SAFE): The skill is designed to process external research data, which creates a potential surface for indirect prompt injection. 1. Ingestion points: Web searches, industry reports, news, and media analysis as specified in SKILL.md. 2. Boundary markers: Absent; there are no specific delimiters to isolate external data. 3. Capability inventory: None; the skill is a standalone instruction file with no code or tool-use definitions provided. 4. Sanitization: Absent; the instructions do not specify validation for external content. Severity is downgraded to SAFE because this surface is essential to the primary research purpose and no active exploitation is present.
- [No Code] (SAFE): No executable scripts or binaries were found in the skill folder.
Audit Metadata