social-intelligence
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and Markdown templates. It does not contain any scripts, binaries, or automated command execution logic.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to monitor external, untrusted content from social media platforms (Twitter/X), which constitutes a potential ingestion surface for malicious instructions. However, the risk is mitigated by the following factors:
- Ingestion points: The agent monitors Twitter/X feeds and competitor activity (SKILL.md).
- Boundary markers: The workflow includes an explicit 'Verify' step that instructs the agent to cross-reference signals against official announcements and distinguish rumors from facts.
- Capability inventory: The skill does not define or use any tools that could be abused (e.g., file writes, command execution, or network exfiltration).
- Sanitization: While no technical sanitization is described, the skill's primary output is restricted to Markdown reporting for human review.
Audit Metadata