crosspost
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues were detected. The skill instructions focus on stylistic adaptation and platform constraints.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external text to generate adapted versions, creating a surface for potential instruction injection.\n
- Ingestion points: User-provided articles, posts, and notes in the distribution workflow (SKILL.md).\n
- Boundary markers: Missing explicit delimiters or instructions for the agent to ignore commands within the source text.\n
- Capability inventory: Uses the
x-apiskill, which includes capabilities for publishing to external network services.\n - Sanitization: No input validation or sanitization routines are specified for the ingested content.
Audit Metadata