market-research
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze untrusted data from external sources, including competitor websites, social media conversations, and customer reviews. This content is attacker-controlled and may contain malicious instructions designed to manipulate the agent's output or behavior.
- Ingestion points: instructions to "Analyze their websites, social media, content marketing, and customer reviews" and "Monitor social media for mentions" (SKILL.md).
- Boundary markers: No specific delimiters or instructions to ignore embedded commands within the fetched data are provided.
- Capability inventory: While no scripts are provided in this skill, the agent's base tools (such as web browsing or fetching) would be used to retrieve the external content.
- Sanitization: No sanitization or filtering steps are defined for the retrieved external data.
Audit Metadata