loop-me

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information and project notes to generate content in the workspace, creating a potential surface for indirect prompt injection.
  • Ingestion points: Reads user input and project data from NOTES.md (SKILL.md).
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential injections within the gathered workflow specifications.
  • Capability inventory: The agent is instructed to create, edit, and delete markdown files within the workflows/ directory and update NOTES.md (SKILL.md).
  • Sanitization: No explicit filtering or validation of the ingested user content is defined before it is written to the workspace files.
  • [NO_CODE]: The skill consists only of instructions and configuration files without providing any executable scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 07:25 AM
Security Audit — agent-trust-hub — loop-me