crosspost
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content for adaptation and distribution, creating a surface for potential injection attacks.
- Ingestion points: The skill ingests user-provided text such as articles, launch notes, memos, and changelogs to adapt them for various social media platforms (X, LinkedIn, Threads, Bluesky).
- Boundary markers: There are no explicit boundary markers or instructions defined to prevent the agent from following malicious commands that might be embedded within the source content.
- Capability inventory: The skill references
x-api, indicating a capability to interact with external APIs for publishing content to social media platforms. - Sanitization: The instructions do not include steps for sanitizing, escaping, or validating the input content before processing it into social media posts.
Audit Metadata