market-scanner
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests data from untrusted external sources, creating an attack surface for indirect prompt injection.
- Ingestion points: Step 1 (Scan Sources) includes industry commentary from Twitter/X threads and Hacker News discussions, as well as analyst blogs, which are attacker-controlled environments.
- Boundary markers: The instructions do not specify any delimiters or safety prompts to prevent the agent from following instructions hidden within the scraped content.
- Capability inventory: The agent uses the gathered data to produce strategic briefs, scenario analyses, and recommended actions, all of which could be manipulated by malicious inputs.
- Sanitization: There is no implementation of sanitization or validation logic to filter out potentially harmful instructions from the fetched web content.
- [NO_CODE]: The skill documentation describes a workflow but does not include any executable code or scripts for direct analysis.
Audit Metadata