x-thread-rewrite

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill instructions define a legitimate and transparent process for text transformation without any hidden or malicious behaviors.
  • [NO_CODE]: The skill consists entirely of natural language instructions and markdown templates; it does not include scripts, binary files, or external dependencies.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external essay content, which is a potential surface for indirect prompt injection. However, the impact is minimized by the highly specific output format and the lack of dangerous capabilities like network access or shell execution. * Ingestion points: External Substack essay content loaded during the rewrite workflow. * Boundary markers: None explicitly defined in the instructions. * Capability inventory: Writing a markdown file to a specific local project directory (ops/distribution/). * Sanitization: None; the instructions explicitly request preserving attributions and hedges verbatim.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 02:37 PM
Security Audit — agent-trust-hub — x-thread-rewrite