the-rewrite-room

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the ingestion and processing of untrusted data from external URLs and local filesystem paths through commands such as /rwr:cite, /rwr:author, and /rwr:optimize. This creates an attack surface for indirect prompt injection, where malicious instructions embedded in the processed source material could influence the agent's actions. \n
  • Ingestion points: External source URLs and local project files (Markdown, code, etc.). \n
  • Boundary markers: The skill documentation does not define explicit boundary markers or safety instructions to the agent to ignore instructions within the ingested content. \n
  • Capability inventory: The skill is granted access to powerful tools including Bash, Write, and Edit. \n
  • Sanitization: There is no mention of sanitization, validation, or filtering of the content retrieved from external or local sources.
  • [EXTERNAL_DOWNLOADS]: The /rwr:cite command initiates network requests to retrieve content from arbitrary, user-provided URLs. These operations involve interactions with non-whitelisted external domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 08:42 AM