competitor-ad-research
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructions for gathering competitive intelligence using specific vendor capabilities for Facebook, Google, Twitter, and Instagram. All network interactions are performed through mediated vendor tools (
sandbase_run), and the skill includes explicit instructions to remain in a read-only research mode, preventing unauthorized actions on external platforms. No evidence of malicious code, obfuscation, or credential harvesting was found. - [INDIRECT_PROMPT_INJECTION]: The skill creates a data ingestion surface by processing content from external sources such as social media posts and advertising libraries. While this could theoretically expose the agent to instructions embedded in third-party content, the skill's narrow scope (read-only research) and use of structured capability inspection (
sandbase_inspect) provide a controlled environment for data handling.
Audit Metadata