x-hashtag-research
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted public data from X (Twitter), creating a potential attack surface for indirect prompt injection.
- Ingestion points: Public posts, X cards, and metadata retrieved via X live search (SKILL.md).
- Boundary markers: The instructions lack specific directives for the agent to use delimiters or to ignore potential instructions embedded within the retrieved social media posts.
- Capability inventory: The skill possesses file-writing capabilities, specifically saving raw data to
tmp/and structured notes/assets to theresearch/directory. - Sanitization: No explicit content sanitization or instruction filtering is mentioned for the data being interpolated into the final research notes.
Audit Metadata