reatom-extension-candidates

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and process arbitrary code from a target codebase.
  • Ingestion points: The skill reads and analyzes existing codebase files (referenced in SKILL.md).
  • Boundary markers: The instructions lack explicit delimiters or markers to help the agent distinguish between its instructions and content found within the analyzed files.
  • Capability inventory: The skill has access to the Bash and read tools, providing a pathway for command execution or further file system access if malicious instructions in the code were to be obeyed.
  • Sanitization: No sanitization or filtering logic is provided to validate the content of the files before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 10:14 AM
Security Audit — agent-trust-hub — reatom-extension-candidates