loop-me

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill operates by reading and writing to files within the local workspace, creating a surface where untrusted data could influence agent behavior.
  • Ingestion points: The skill reads context from NOTES.md and workflows/*.md (SKILL.md).
  • Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate between file content and agent instructions.
  • Capability inventory: The skill allows the agent to read, create, edit, and delete files in the workflows/ directory (SKILL.md).
  • Sanitization: There are no requirements for the agent to sanitize or validate the content retrieved from the workspace before processing it.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 10:28 AM
Security Audit — agent-trust-hub — loop-me