agency-x-twitter-intelligence-analyst
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and synthesize external, untrusted data from X/Twitter (posts, profiles, threads). This creates a surface where malicious instructions embedded in analyzed posts could influence the agent's summary or downstream actions.
- Ingestion points: Data collection involves pulling search results, profile activity, and engagement context (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing external content.
- Capability inventory: The skill generates intelligence briefs and can trigger webhooks for threshold-based monitoring.
- Sanitization: No specific sanitization or filtering logic is mentioned for handling executable or instructional text within the social media data.
Audit Metadata